| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 645, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004651162790697674, |
| "grad_norm": 19.568607330322266, |
| "learning_rate": 0.0, |
| "loss": 0.842, |
| "mean_token_accuracy": 0.8234314918518066, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.009302325581395349, |
| "grad_norm": 21.537723541259766, |
| "learning_rate": 1.5384615384615387e-07, |
| "loss": 0.8778, |
| "mean_token_accuracy": 0.8231534361839294, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.013953488372093023, |
| "grad_norm": 19.284854888916016, |
| "learning_rate": 3.0769230769230774e-07, |
| "loss": 0.8509, |
| "mean_token_accuracy": 0.8327401876449585, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.018604651162790697, |
| "grad_norm": 18.94418716430664, |
| "learning_rate": 4.615384615384616e-07, |
| "loss": 0.8236, |
| "mean_token_accuracy": 0.8300436735153198, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.023255813953488372, |
| "grad_norm": 22.949390411376953, |
| "learning_rate": 6.153846153846155e-07, |
| "loss": 0.9618, |
| "mean_token_accuracy": 0.8052875399589539, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.027906976744186046, |
| "grad_norm": 22.52558135986328, |
| "learning_rate": 7.692307692307694e-07, |
| "loss": 0.8629, |
| "mean_token_accuracy": 0.8194347620010376, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.03255813953488372, |
| "grad_norm": 21.534772872924805, |
| "learning_rate": 9.230769230769232e-07, |
| "loss": 0.9071, |
| "mean_token_accuracy": 0.8167065978050232, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.037209302325581395, |
| "grad_norm": 15.813007354736328, |
| "learning_rate": 1.076923076923077e-06, |
| "loss": 0.8068, |
| "mean_token_accuracy": 0.8270938992500305, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.04186046511627907, |
| "grad_norm": 14.425293922424316, |
| "learning_rate": 1.230769230769231e-06, |
| "loss": 0.7203, |
| "mean_token_accuracy": 0.8420020937919617, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.046511627906976744, |
| "grad_norm": 15.85297966003418, |
| "learning_rate": 1.3846153846153848e-06, |
| "loss": 0.7537, |
| "mean_token_accuracy": 0.8397467732429504, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05116279069767442, |
| "grad_norm": 15.877695083618164, |
| "learning_rate": 1.5384615384615387e-06, |
| "loss": 0.7201, |
| "mean_token_accuracy": 0.8532203435897827, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.05581395348837209, |
| "grad_norm": 11.435991287231445, |
| "learning_rate": 1.6923076923076926e-06, |
| "loss": 0.6885, |
| "mean_token_accuracy": 0.8493710160255432, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.06046511627906977, |
| "grad_norm": 11.014802932739258, |
| "learning_rate": 1.8461538461538465e-06, |
| "loss": 0.6633, |
| "mean_token_accuracy": 0.8415761590003967, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.06511627906976744, |
| "grad_norm": 9.7716064453125, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.6095, |
| "mean_token_accuracy": 0.8588042855262756, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "grad_norm": 9.165430068969727, |
| "learning_rate": 2.153846153846154e-06, |
| "loss": 0.5607, |
| "mean_token_accuracy": 0.8693761229515076, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.07441860465116279, |
| "grad_norm": 10.080243110656738, |
| "learning_rate": 2.307692307692308e-06, |
| "loss": 0.5113, |
| "mean_token_accuracy": 0.8672978281974792, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.07906976744186046, |
| "grad_norm": 10.527639389038086, |
| "learning_rate": 2.461538461538462e-06, |
| "loss": 0.4415, |
| "mean_token_accuracy": 0.8862723708152771, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.08372093023255814, |
| "grad_norm": 7.268032073974609, |
| "learning_rate": 2.615384615384616e-06, |
| "loss": 0.4505, |
| "mean_token_accuracy": 0.8736571073532104, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.08837209302325581, |
| "grad_norm": 7.092712879180908, |
| "learning_rate": 2.7692307692307697e-06, |
| "loss": 0.4496, |
| "mean_token_accuracy": 0.8755980730056763, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.09302325581395349, |
| "grad_norm": 4.317747592926025, |
| "learning_rate": 2.9230769230769236e-06, |
| "loss": 0.3947, |
| "mean_token_accuracy": 0.8856920599937439, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09767441860465116, |
| "grad_norm": 4.245256423950195, |
| "learning_rate": 3.0769230769230774e-06, |
| "loss": 0.4397, |
| "mean_token_accuracy": 0.8684402108192444, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.10232558139534884, |
| "grad_norm": 3.8611507415771484, |
| "learning_rate": 3.2307692307692313e-06, |
| "loss": 0.3792, |
| "mean_token_accuracy": 0.8823331594467163, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.10697674418604651, |
| "grad_norm": 4.211703300476074, |
| "learning_rate": 3.384615384615385e-06, |
| "loss": 0.3552, |
| "mean_token_accuracy": 0.8943809270858765, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.11162790697674418, |
| "grad_norm": 3.5800399780273438, |
| "learning_rate": 3.538461538461539e-06, |
| "loss": 0.3806, |
| "mean_token_accuracy": 0.8816819787025452, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.11627906976744186, |
| "grad_norm": 3.5746443271636963, |
| "learning_rate": 3.692307692307693e-06, |
| "loss": 0.3583, |
| "mean_token_accuracy": 0.8919854164123535, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12093023255813953, |
| "grad_norm": 3.409257411956787, |
| "learning_rate": 3.846153846153847e-06, |
| "loss": 0.343, |
| "mean_token_accuracy": 0.8980305790901184, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.12558139534883722, |
| "grad_norm": 3.196232318878174, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.3653, |
| "mean_token_accuracy": 0.8912448883056641, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.13023255813953488, |
| "grad_norm": 3.6028528213500977, |
| "learning_rate": 4.1538461538461545e-06, |
| "loss": 0.3653, |
| "mean_token_accuracy": 0.8908067345619202, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.13488372093023257, |
| "grad_norm": 3.0673670768737793, |
| "learning_rate": 4.307692307692308e-06, |
| "loss": 0.3824, |
| "mean_token_accuracy": 0.8820690512657166, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.13953488372093023, |
| "grad_norm": 3.353994369506836, |
| "learning_rate": 4.461538461538462e-06, |
| "loss": 0.3762, |
| "mean_token_accuracy": 0.881018877029419, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14418604651162792, |
| "grad_norm": 3.5132193565368652, |
| "learning_rate": 4.615384615384616e-06, |
| "loss": 0.3993, |
| "mean_token_accuracy": 0.8744673132896423, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.14883720930232558, |
| "grad_norm": 3.0335817337036133, |
| "learning_rate": 4.76923076923077e-06, |
| "loss": 0.3241, |
| "mean_token_accuracy": 0.8991076350212097, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.15348837209302327, |
| "grad_norm": 3.8447790145874023, |
| "learning_rate": 4.923076923076924e-06, |
| "loss": 0.356, |
| "mean_token_accuracy": 0.8917796015739441, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.15813953488372093, |
| "grad_norm": 2.874586820602417, |
| "learning_rate": 5.076923076923077e-06, |
| "loss": 0.3098, |
| "mean_token_accuracy": 0.903138279914856, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.16279069767441862, |
| "grad_norm": 3.0539486408233643, |
| "learning_rate": 5.230769230769232e-06, |
| "loss": 0.3544, |
| "mean_token_accuracy": 0.8905218243598938, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.16744186046511628, |
| "grad_norm": 2.976952314376831, |
| "learning_rate": 5.384615384615385e-06, |
| "loss": 0.3361, |
| "mean_token_accuracy": 0.8934714198112488, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.17209302325581396, |
| "grad_norm": 3.0622878074645996, |
| "learning_rate": 5.538461538461539e-06, |
| "loss": 0.3236, |
| "mean_token_accuracy": 0.8999074697494507, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.17674418604651163, |
| "grad_norm": 3.257957935333252, |
| "learning_rate": 5.692307692307692e-06, |
| "loss": 0.343, |
| "mean_token_accuracy": 0.8923910856246948, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.1813953488372093, |
| "grad_norm": 3.007553815841675, |
| "learning_rate": 5.846153846153847e-06, |
| "loss": 0.3164, |
| "mean_token_accuracy": 0.9010202288627625, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.18604651162790697, |
| "grad_norm": 2.944952964782715, |
| "learning_rate": 6e-06, |
| "loss": 0.3467, |
| "mean_token_accuracy": 0.8913513422012329, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.19069767441860466, |
| "grad_norm": 2.9425339698791504, |
| "learning_rate": 6.153846153846155e-06, |
| "loss": 0.338, |
| "mean_token_accuracy": 0.9000540375709534, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.19534883720930232, |
| "grad_norm": 3.1975269317626953, |
| "learning_rate": 6.307692307692308e-06, |
| "loss": 0.3408, |
| "mean_token_accuracy": 0.898595929145813, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 3.0284111499786377, |
| "learning_rate": 6.461538461538463e-06, |
| "loss": 0.3112, |
| "mean_token_accuracy": 0.9032689929008484, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.20465116279069767, |
| "grad_norm": 2.8465347290039062, |
| "learning_rate": 6.615384615384616e-06, |
| "loss": 0.3387, |
| "mean_token_accuracy": 0.9016018509864807, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.20930232558139536, |
| "grad_norm": 3.0937321186065674, |
| "learning_rate": 6.76923076923077e-06, |
| "loss": 0.3037, |
| "mean_token_accuracy": 0.906658947467804, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.21395348837209302, |
| "grad_norm": 2.862903118133545, |
| "learning_rate": 6.923076923076923e-06, |
| "loss": 0.3115, |
| "mean_token_accuracy": 0.9050519466400146, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.2186046511627907, |
| "grad_norm": 2.914771318435669, |
| "learning_rate": 7.076923076923078e-06, |
| "loss": 0.317, |
| "mean_token_accuracy": 0.9020901918411255, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.22325581395348837, |
| "grad_norm": 2.9237124919891357, |
| "learning_rate": 7.230769230769231e-06, |
| "loss": 0.3292, |
| "mean_token_accuracy": 0.9041584730148315, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.22790697674418606, |
| "grad_norm": 2.9312398433685303, |
| "learning_rate": 7.384615384615386e-06, |
| "loss": 0.3202, |
| "mean_token_accuracy": 0.9016806483268738, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.23255813953488372, |
| "grad_norm": 2.9532058238983154, |
| "learning_rate": 7.538461538461539e-06, |
| "loss": 0.3293, |
| "mean_token_accuracy": 0.9001582264900208, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2372093023255814, |
| "grad_norm": 3.0990428924560547, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3411, |
| "mean_token_accuracy": 0.8866774439811707, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.24186046511627907, |
| "grad_norm": 2.87052059173584, |
| "learning_rate": 7.846153846153847e-06, |
| "loss": 0.3395, |
| "mean_token_accuracy": 0.8905250430107117, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.24651162790697675, |
| "grad_norm": 3.011493682861328, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.3261, |
| "mean_token_accuracy": 0.899782121181488, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.25116279069767444, |
| "grad_norm": 2.943223237991333, |
| "learning_rate": 8.153846153846154e-06, |
| "loss": 0.3414, |
| "mean_token_accuracy": 0.8933002352714539, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.2558139534883721, |
| "grad_norm": 2.8687915802001953, |
| "learning_rate": 8.307692307692309e-06, |
| "loss": 0.3425, |
| "mean_token_accuracy": 0.8924914598464966, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.26046511627906976, |
| "grad_norm": 2.947930335998535, |
| "learning_rate": 8.461538461538462e-06, |
| "loss": 0.3338, |
| "mean_token_accuracy": 0.8992005586624146, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.2651162790697674, |
| "grad_norm": 2.625805616378784, |
| "learning_rate": 8.615384615384617e-06, |
| "loss": 0.2921, |
| "mean_token_accuracy": 0.9067084193229675, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.26976744186046514, |
| "grad_norm": 2.7415740489959717, |
| "learning_rate": 8.76923076923077e-06, |
| "loss": 0.3208, |
| "mean_token_accuracy": 0.8967901468276978, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.2744186046511628, |
| "grad_norm": 3.0610153675079346, |
| "learning_rate": 8.923076923076925e-06, |
| "loss": 0.3079, |
| "mean_token_accuracy": 0.9053909182548523, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.27906976744186046, |
| "grad_norm": 2.8837437629699707, |
| "learning_rate": 9.076923076923078e-06, |
| "loss": 0.3223, |
| "mean_token_accuracy": 0.8960626721382141, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2837209302325581, |
| "grad_norm": 3.0495381355285645, |
| "learning_rate": 9.230769230769232e-06, |
| "loss": 0.3543, |
| "mean_token_accuracy": 0.8843302726745605, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.28837209302325584, |
| "grad_norm": 3.0705480575561523, |
| "learning_rate": 9.384615384615385e-06, |
| "loss": 0.3536, |
| "mean_token_accuracy": 0.8863232731819153, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.2930232558139535, |
| "grad_norm": 2.8244340419769287, |
| "learning_rate": 9.53846153846154e-06, |
| "loss": 0.3214, |
| "mean_token_accuracy": 0.900137722492218, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.29767441860465116, |
| "grad_norm": 2.8263750076293945, |
| "learning_rate": 9.692307692307693e-06, |
| "loss": 0.3219, |
| "mean_token_accuracy": 0.8964273929595947, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.3023255813953488, |
| "grad_norm": 3.0754854679107666, |
| "learning_rate": 9.846153846153848e-06, |
| "loss": 0.3427, |
| "mean_token_accuracy": 0.8874080181121826, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.30697674418604654, |
| "grad_norm": 2.6351478099823, |
| "learning_rate": 1e-05, |
| "loss": 0.3105, |
| "mean_token_accuracy": 0.8933923840522766, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.3116279069767442, |
| "grad_norm": 2.8327081203460693, |
| "learning_rate": 9.999933987646821e-06, |
| "loss": 0.3296, |
| "mean_token_accuracy": 0.8912156224250793, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.31627906976744186, |
| "grad_norm": 2.7764129638671875, |
| "learning_rate": 9.99973595252401e-06, |
| "loss": 0.2963, |
| "mean_token_accuracy": 0.9016897082328796, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.3209302325581395, |
| "grad_norm": 2.8871490955352783, |
| "learning_rate": 9.999405900441683e-06, |
| "loss": 0.3152, |
| "mean_token_accuracy": 0.8972193002700806, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.32558139534883723, |
| "grad_norm": 2.9388067722320557, |
| "learning_rate": 9.998943841083179e-06, |
| "loss": 0.3187, |
| "mean_token_accuracy": 0.8915014863014221, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.3302325581395349, |
| "grad_norm": 2.861207962036133, |
| "learning_rate": 9.99834978800478e-06, |
| "loss": 0.3152, |
| "mean_token_accuracy": 0.8957569599151611, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.33488372093023255, |
| "grad_norm": 2.725429058074951, |
| "learning_rate": 9.997623758635298e-06, |
| "loss": 0.3155, |
| "mean_token_accuracy": 0.8980090618133545, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.3395348837209302, |
| "grad_norm": 2.838580369949341, |
| "learning_rate": 9.996765774275587e-06, |
| "loss": 0.3398, |
| "mean_token_accuracy": 0.8817829489707947, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.34418604651162793, |
| "grad_norm": 2.6265110969543457, |
| "learning_rate": 9.995775860097897e-06, |
| "loss": 0.2922, |
| "mean_token_accuracy": 0.8991727232933044, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.3488372093023256, |
| "grad_norm": 2.9625837802886963, |
| "learning_rate": 9.994654045145142e-06, |
| "loss": 0.3265, |
| "mean_token_accuracy": 0.8913161158561707, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.35348837209302325, |
| "grad_norm": 2.6737451553344727, |
| "learning_rate": 9.993400362330058e-06, |
| "loss": 0.293, |
| "mean_token_accuracy": 0.9017840027809143, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.3581395348837209, |
| "grad_norm": 2.600137710571289, |
| "learning_rate": 9.992014848434221e-06, |
| "loss": 0.3134, |
| "mean_token_accuracy": 0.8939000368118286, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.3627906976744186, |
| "grad_norm": 2.5492331981658936, |
| "learning_rate": 9.990497544106981e-06, |
| "loss": 0.278, |
| "mean_token_accuracy": 0.905031681060791, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.3674418604651163, |
| "grad_norm": 2.828934669494629, |
| "learning_rate": 9.988848493864259e-06, |
| "loss": 0.3139, |
| "mean_token_accuracy": 0.8893573880195618, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.37209302325581395, |
| "grad_norm": 2.4408745765686035, |
| "learning_rate": 9.987067746087251e-06, |
| "loss": 0.3349, |
| "mean_token_accuracy": 0.8832064867019653, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3767441860465116, |
| "grad_norm": 2.7932300567626953, |
| "learning_rate": 9.985155353021004e-06, |
| "loss": 0.2888, |
| "mean_token_accuracy": 0.9002993106842041, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.3813953488372093, |
| "grad_norm": 2.693359613418579, |
| "learning_rate": 9.983111370772877e-06, |
| "loss": 0.2828, |
| "mean_token_accuracy": 0.9031432867050171, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.386046511627907, |
| "grad_norm": 2.4886722564697266, |
| "learning_rate": 9.980935859310907e-06, |
| "loss": 0.2906, |
| "mean_token_accuracy": 0.9039763808250427, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.39069767441860465, |
| "grad_norm": 2.453582525253296, |
| "learning_rate": 9.97862888246204e-06, |
| "loss": 0.3303, |
| "mean_token_accuracy": 0.8835755586624146, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.3953488372093023, |
| "grad_norm": 2.423192024230957, |
| "learning_rate": 9.976190507910265e-06, |
| "loss": 0.3036, |
| "mean_token_accuracy": 0.8907879590988159, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 2.716904878616333, |
| "learning_rate": 9.97362080719462e-06, |
| "loss": 0.333, |
| "mean_token_accuracy": 0.8917351365089417, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.4046511627906977, |
| "grad_norm": 2.4398062229156494, |
| "learning_rate": 9.970919855707103e-06, |
| "loss": 0.3071, |
| "mean_token_accuracy": 0.8877987861633301, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.40930232558139534, |
| "grad_norm": 2.614738941192627, |
| "learning_rate": 9.968087732690452e-06, |
| "loss": 0.3566, |
| "mean_token_accuracy": 0.8800138831138611, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.413953488372093, |
| "grad_norm": 2.467711925506592, |
| "learning_rate": 9.965124521235827e-06, |
| "loss": 0.305, |
| "mean_token_accuracy": 0.9028013944625854, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.4186046511627907, |
| "grad_norm": 2.5902044773101807, |
| "learning_rate": 9.962030308280363e-06, |
| "loss": 0.2639, |
| "mean_token_accuracy": 0.9111554026603699, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4232558139534884, |
| "grad_norm": 2.4866185188293457, |
| "learning_rate": 9.958805184604631e-06, |
| "loss": 0.2698, |
| "mean_token_accuracy": 0.9070945978164673, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.42790697674418604, |
| "grad_norm": 2.5046956539154053, |
| "learning_rate": 9.955449244829966e-06, |
| "loss": 0.322, |
| "mean_token_accuracy": 0.8915765881538391, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.4325581395348837, |
| "grad_norm": 2.4573545455932617, |
| "learning_rate": 9.95196258741569e-06, |
| "loss": 0.2948, |
| "mean_token_accuracy": 0.898975133895874, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.4372093023255814, |
| "grad_norm": 2.4542694091796875, |
| "learning_rate": 9.948345314656234e-06, |
| "loss": 0.3093, |
| "mean_token_accuracy": 0.896518349647522, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.4418604651162791, |
| "grad_norm": 2.5495047569274902, |
| "learning_rate": 9.94459753267812e-06, |
| "loss": 0.3092, |
| "mean_token_accuracy": 0.8926985263824463, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.44651162790697674, |
| "grad_norm": 2.413846015930176, |
| "learning_rate": 9.94071935143687e-06, |
| "loss": 0.292, |
| "mean_token_accuracy": 0.9006398916244507, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.4511627906976744, |
| "grad_norm": 2.5379788875579834, |
| "learning_rate": 9.936710884713752e-06, |
| "loss": 0.2552, |
| "mean_token_accuracy": 0.9097174406051636, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.4558139534883721, |
| "grad_norm": 2.4800572395324707, |
| "learning_rate": 9.932572250112469e-06, |
| "loss": 0.3124, |
| "mean_token_accuracy": 0.8870939016342163, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.4604651162790698, |
| "grad_norm": 2.299506425857544, |
| "learning_rate": 9.92830356905569e-06, |
| "loss": 0.2613, |
| "mean_token_accuracy": 0.9084261059761047, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.46511627906976744, |
| "grad_norm": 2.372338056564331, |
| "learning_rate": 9.923904966781496e-06, |
| "loss": 0.3313, |
| "mean_token_accuracy": 0.8863078951835632, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4697674418604651, |
| "grad_norm": 2.4246954917907715, |
| "learning_rate": 9.919376572339703e-06, |
| "loss": 0.3164, |
| "mean_token_accuracy": 0.8909768462181091, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.4744186046511628, |
| "grad_norm": 2.382747173309326, |
| "learning_rate": 9.914718518588076e-06, |
| "loss": 0.312, |
| "mean_token_accuracy": 0.8973370790481567, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.4790697674418605, |
| "grad_norm": 2.20865797996521, |
| "learning_rate": 9.909930942188436e-06, |
| "loss": 0.3017, |
| "mean_token_accuracy": 0.8977475166320801, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.48372093023255813, |
| "grad_norm": 2.2108991146087646, |
| "learning_rate": 9.905013983602639e-06, |
| "loss": 0.2822, |
| "mean_token_accuracy": 0.9046753644943237, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.4883720930232558, |
| "grad_norm": 2.45776104927063, |
| "learning_rate": 9.899967787088468e-06, |
| "loss": 0.3172, |
| "mean_token_accuracy": 0.8890208005905151, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.4930232558139535, |
| "grad_norm": 2.4246809482574463, |
| "learning_rate": 9.89479250069539e-06, |
| "loss": 0.2847, |
| "mean_token_accuracy": 0.9031876921653748, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.49767441860465117, |
| "grad_norm": 2.4469594955444336, |
| "learning_rate": 9.889488276260222e-06, |
| "loss": 0.3474, |
| "mean_token_accuracy": 0.8859800100326538, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.5023255813953489, |
| "grad_norm": 2.5260751247406006, |
| "learning_rate": 9.88405526940267e-06, |
| "loss": 0.3265, |
| "mean_token_accuracy": 0.884105384349823, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.5069767441860465, |
| "grad_norm": 2.5180299282073975, |
| "learning_rate": 9.87849363952076e-06, |
| "loss": 0.2824, |
| "mean_token_accuracy": 0.9007551074028015, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.5116279069767442, |
| "grad_norm": 2.5075199604034424, |
| "learning_rate": 9.872803549786177e-06, |
| "loss": 0.2946, |
| "mean_token_accuracy": 0.8951205611228943, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.5162790697674419, |
| "grad_norm": 2.4692704677581787, |
| "learning_rate": 9.866985167139453e-06, |
| "loss": 0.3182, |
| "mean_token_accuracy": 0.8877219557762146, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.5209302325581395, |
| "grad_norm": 2.3963942527770996, |
| "learning_rate": 9.861038662285093e-06, |
| "loss": 0.2969, |
| "mean_token_accuracy": 0.8966950178146362, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.5255813953488372, |
| "grad_norm": 2.3317747116088867, |
| "learning_rate": 9.854964209686555e-06, |
| "loss": 0.3333, |
| "mean_token_accuracy": 0.891633927822113, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.5302325581395348, |
| "grad_norm": 2.317647933959961, |
| "learning_rate": 9.848761987561132e-06, |
| "loss": 0.3076, |
| "mean_token_accuracy": 0.8995808362960815, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.5348837209302325, |
| "grad_norm": 2.637216567993164, |
| "learning_rate": 9.842432177874725e-06, |
| "loss": 0.3078, |
| "mean_token_accuracy": 0.8890925645828247, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.5395348837209303, |
| "grad_norm": 2.7842369079589844, |
| "learning_rate": 9.835974966336504e-06, |
| "loss": 0.3121, |
| "mean_token_accuracy": 0.8958715796470642, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.5441860465116279, |
| "grad_norm": 2.725388288497925, |
| "learning_rate": 9.82939054239346e-06, |
| "loss": 0.3233, |
| "mean_token_accuracy": 0.8867715001106262, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.5488372093023256, |
| "grad_norm": 2.2746381759643555, |
| "learning_rate": 9.822679099224844e-06, |
| "loss": 0.2699, |
| "mean_token_accuracy": 0.9086083769798279, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.5534883720930233, |
| "grad_norm": 2.4101691246032715, |
| "learning_rate": 9.815840833736508e-06, |
| "loss": 0.26, |
| "mean_token_accuracy": 0.9082334637641907, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.5581395348837209, |
| "grad_norm": 2.3375160694122314, |
| "learning_rate": 9.808875946555109e-06, |
| "loss": 0.2658, |
| "mean_token_accuracy": 0.9081822633743286, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5627906976744186, |
| "grad_norm": 2.2656409740448, |
| "learning_rate": 9.801784642022254e-06, |
| "loss": 0.2374, |
| "mean_token_accuracy": 0.9136148691177368, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.5674418604651162, |
| "grad_norm": 2.5492942333221436, |
| "learning_rate": 9.794567128188466e-06, |
| "loss": 0.3194, |
| "mean_token_accuracy": 0.8901216983795166, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.5720930232558139, |
| "grad_norm": 2.8390772342681885, |
| "learning_rate": 9.787223616807118e-06, |
| "loss": 0.3522, |
| "mean_token_accuracy": 0.8756738901138306, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.5767441860465117, |
| "grad_norm": 2.3636889457702637, |
| "learning_rate": 9.779754323328192e-06, |
| "loss": 0.3166, |
| "mean_token_accuracy": 0.8895965814590454, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.5813953488372093, |
| "grad_norm": 2.4303550720214844, |
| "learning_rate": 9.772159466891971e-06, |
| "loss": 0.2507, |
| "mean_token_accuracy": 0.9103531241416931, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.586046511627907, |
| "grad_norm": 3.1228110790252686, |
| "learning_rate": 9.764439270322612e-06, |
| "loss": 0.3337, |
| "mean_token_accuracy": 0.8896551728248596, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.5906976744186047, |
| "grad_norm": 2.389329433441162, |
| "learning_rate": 9.756593960121598e-06, |
| "loss": 0.2601, |
| "mean_token_accuracy": 0.912638783454895, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.5953488372093023, |
| "grad_norm": 2.473677635192871, |
| "learning_rate": 9.748623766461101e-06, |
| "loss": 0.3098, |
| "mean_token_accuracy": 0.89825040102005, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 2.882704973220825, |
| "learning_rate": 9.740528923177227e-06, |
| "loss": 0.3681, |
| "mean_token_accuracy": 0.8829707503318787, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.6046511627906976, |
| "grad_norm": 2.7584638595581055, |
| "learning_rate": 9.732309667763158e-06, |
| "loss": 0.295, |
| "mean_token_accuracy": 0.8920313119888306, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.6093023255813953, |
| "grad_norm": 2.507779121398926, |
| "learning_rate": 9.723966241362178e-06, |
| "loss": 0.2819, |
| "mean_token_accuracy": 0.9021470546722412, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.6139534883720931, |
| "grad_norm": 2.3873088359832764, |
| "learning_rate": 9.7154988887606e-06, |
| "loss": 0.2841, |
| "mean_token_accuracy": 0.8999173045158386, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.6186046511627907, |
| "grad_norm": 2.327904224395752, |
| "learning_rate": 9.706907858380593e-06, |
| "loss": 0.3182, |
| "mean_token_accuracy": 0.8869202733039856, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.6232558139534884, |
| "grad_norm": 2.4665448665618896, |
| "learning_rate": 9.69819340227288e-06, |
| "loss": 0.3211, |
| "mean_token_accuracy": 0.8939599394798279, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.627906976744186, |
| "grad_norm": 2.293694019317627, |
| "learning_rate": 9.68935577610935e-06, |
| "loss": 0.3098, |
| "mean_token_accuracy": 0.8957222700119019, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.6325581395348837, |
| "grad_norm": 2.5069773197174072, |
| "learning_rate": 9.680395239175563e-06, |
| "loss": 0.3054, |
| "mean_token_accuracy": 0.8952414393424988, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.6372093023255814, |
| "grad_norm": 2.3153645992279053, |
| "learning_rate": 9.671312054363126e-06, |
| "loss": 0.2976, |
| "mean_token_accuracy": 0.899829626083374, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.641860465116279, |
| "grad_norm": 2.233323812484741, |
| "learning_rate": 9.662106488162001e-06, |
| "loss": 0.3034, |
| "mean_token_accuracy": 0.8928571343421936, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.6465116279069767, |
| "grad_norm": 2.3756513595581055, |
| "learning_rate": 9.652778810652669e-06, |
| "loss": 0.284, |
| "mean_token_accuracy": 0.9001284837722778, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.6511627906976745, |
| "grad_norm": 2.373886823654175, |
| "learning_rate": 9.643329295498215e-06, |
| "loss": 0.3215, |
| "mean_token_accuracy": 0.890358567237854, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6558139534883721, |
| "grad_norm": 2.4615867137908936, |
| "learning_rate": 9.633758219936299e-06, |
| "loss": 0.3237, |
| "mean_token_accuracy": 0.8895444273948669, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.6604651162790698, |
| "grad_norm": 2.5071775913238525, |
| "learning_rate": 9.624065864771017e-06, |
| "loss": 0.2943, |
| "mean_token_accuracy": 0.9009695053100586, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.6651162790697674, |
| "grad_norm": 2.4051311016082764, |
| "learning_rate": 9.614252514364671e-06, |
| "loss": 0.282, |
| "mean_token_accuracy": 0.8996679186820984, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.6697674418604651, |
| "grad_norm": 2.5493178367614746, |
| "learning_rate": 9.604318456629415e-06, |
| "loss": 0.363, |
| "mean_token_accuracy": 0.8800684213638306, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.6744186046511628, |
| "grad_norm": 2.582982301712036, |
| "learning_rate": 9.594263983018818e-06, |
| "loss": 0.3378, |
| "mean_token_accuracy": 0.8826906085014343, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.6790697674418604, |
| "grad_norm": 2.471052885055542, |
| "learning_rate": 9.584089388519307e-06, |
| "loss": 0.3545, |
| "mean_token_accuracy": 0.8743756413459778, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.6837209302325581, |
| "grad_norm": 2.5069751739501953, |
| "learning_rate": 9.573794971641518e-06, |
| "loss": 0.2964, |
| "mean_token_accuracy": 0.8944962024688721, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.6883720930232559, |
| "grad_norm": 2.7452809810638428, |
| "learning_rate": 9.563381034411529e-06, |
| "loss": 0.2885, |
| "mean_token_accuracy": 0.9012883305549622, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.6930232558139535, |
| "grad_norm": 2.500969886779785, |
| "learning_rate": 9.55284788236201e-06, |
| "loss": 0.3279, |
| "mean_token_accuracy": 0.8895537853240967, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.6976744186046512, |
| "grad_norm": 2.6518476009368896, |
| "learning_rate": 9.542195824523251e-06, |
| "loss": 0.2993, |
| "mean_token_accuracy": 0.895342230796814, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7023255813953488, |
| "grad_norm": 2.216704845428467, |
| "learning_rate": 9.531425173414095e-06, |
| "loss": 0.2912, |
| "mean_token_accuracy": 0.8971017003059387, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.7069767441860465, |
| "grad_norm": 2.8981404304504395, |
| "learning_rate": 9.520536245032783e-06, |
| "loss": 0.3483, |
| "mean_token_accuracy": 0.8798250555992126, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.7116279069767442, |
| "grad_norm": 2.808007001876831, |
| "learning_rate": 9.509529358847655e-06, |
| "loss": 0.3235, |
| "mean_token_accuracy": 0.8890100121498108, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.7162790697674418, |
| "grad_norm": 2.2912731170654297, |
| "learning_rate": 9.498404837787811e-06, |
| "loss": 0.2957, |
| "mean_token_accuracy": 0.8959488868713379, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.7209302325581395, |
| "grad_norm": 2.1323370933532715, |
| "learning_rate": 9.48716300823361e-06, |
| "loss": 0.2722, |
| "mean_token_accuracy": 0.9088647961616516, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.7255813953488373, |
| "grad_norm": 2.3741555213928223, |
| "learning_rate": 9.475804200007104e-06, |
| "loss": 0.2523, |
| "mean_token_accuracy": 0.9077244400978088, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.7302325581395349, |
| "grad_norm": 2.571829080581665, |
| "learning_rate": 9.464328746362367e-06, |
| "loss": 0.3139, |
| "mean_token_accuracy": 0.8919800519943237, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.7348837209302326, |
| "grad_norm": 2.3718228340148926, |
| "learning_rate": 9.452736983975708e-06, |
| "loss": 0.3006, |
| "mean_token_accuracy": 0.9011486172676086, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.7395348837209302, |
| "grad_norm": 2.3102355003356934, |
| "learning_rate": 9.441029252935804e-06, |
| "loss": 0.3169, |
| "mean_token_accuracy": 0.8904637098312378, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.7441860465116279, |
| "grad_norm": 2.3063647747039795, |
| "learning_rate": 9.429205896733705e-06, |
| "loss": 0.3344, |
| "mean_token_accuracy": 0.885936975479126, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7488372093023256, |
| "grad_norm": 2.2388534545898438, |
| "learning_rate": 9.417267262252775e-06, |
| "loss": 0.2618, |
| "mean_token_accuracy": 0.9093095064163208, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.7534883720930232, |
| "grad_norm": 2.311589241027832, |
| "learning_rate": 9.405213699758507e-06, |
| "loss": 0.2951, |
| "mean_token_accuracy": 0.9044934511184692, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.7581395348837209, |
| "grad_norm": 2.6392147541046143, |
| "learning_rate": 9.393045562888245e-06, |
| "loss": 0.3072, |
| "mean_token_accuracy": 0.8980139493942261, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.7627906976744186, |
| "grad_norm": 2.4263360500335693, |
| "learning_rate": 9.380763208640809e-06, |
| "loss": 0.3182, |
| "mean_token_accuracy": 0.89084792137146, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.7674418604651163, |
| "grad_norm": 2.5029895305633545, |
| "learning_rate": 9.368366997366027e-06, |
| "loss": 0.3163, |
| "mean_token_accuracy": 0.8866799473762512, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.772093023255814, |
| "grad_norm": 2.336146593093872, |
| "learning_rate": 9.355857292754152e-06, |
| "loss": 0.3092, |
| "mean_token_accuracy": 0.8928571343421936, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.7767441860465116, |
| "grad_norm": 2.218172550201416, |
| "learning_rate": 9.343234461825204e-06, |
| "loss": 0.2906, |
| "mean_token_accuracy": 0.9058730006217957, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.7813953488372093, |
| "grad_norm": 2.5669257640838623, |
| "learning_rate": 9.330498874918191e-06, |
| "loss": 0.3321, |
| "mean_token_accuracy": 0.8863449096679688, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.786046511627907, |
| "grad_norm": 2.513970136642456, |
| "learning_rate": 9.317650905680254e-06, |
| "loss": 0.2676, |
| "mean_token_accuracy": 0.9085434675216675, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.7906976744186046, |
| "grad_norm": 2.1640465259552, |
| "learning_rate": 9.304690931055694e-06, |
| "loss": 0.274, |
| "mean_token_accuracy": 0.9004696607589722, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.7953488372093023, |
| "grad_norm": 2.511218547821045, |
| "learning_rate": 9.29161933127492e-06, |
| "loss": 0.3194, |
| "mean_token_accuracy": 0.8944977521896362, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 2.421499252319336, |
| "learning_rate": 9.278436489843298e-06, |
| "loss": 0.2887, |
| "mean_token_accuracy": 0.9034446477890015, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.8046511627906977, |
| "grad_norm": 2.588841199874878, |
| "learning_rate": 9.265142793529883e-06, |
| "loss": 0.3064, |
| "mean_token_accuracy": 0.8959047198295593, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.8093023255813954, |
| "grad_norm": 2.45721435546875, |
| "learning_rate": 9.251738632356086e-06, |
| "loss": 0.2945, |
| "mean_token_accuracy": 0.8972444534301758, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.813953488372093, |
| "grad_norm": 2.337759256362915, |
| "learning_rate": 9.238224399584232e-06, |
| "loss": 0.3035, |
| "mean_token_accuracy": 0.8876973390579224, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.8186046511627907, |
| "grad_norm": 2.4137725830078125, |
| "learning_rate": 9.224600491706009e-06, |
| "loss": 0.2831, |
| "mean_token_accuracy": 0.9046387076377869, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.8232558139534883, |
| "grad_norm": 2.3806352615356445, |
| "learning_rate": 9.210867308430847e-06, |
| "loss": 0.3307, |
| "mean_token_accuracy": 0.8875255584716797, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.827906976744186, |
| "grad_norm": 2.5038254261016846, |
| "learning_rate": 9.197025252674192e-06, |
| "loss": 0.2855, |
| "mean_token_accuracy": 0.9022055268287659, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.8325581395348837, |
| "grad_norm": 2.2400872707366943, |
| "learning_rate": 9.183074730545674e-06, |
| "loss": 0.3032, |
| "mean_token_accuracy": 0.8980777859687805, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.8372093023255814, |
| "grad_norm": 2.3404793739318848, |
| "learning_rate": 9.169016151337202e-06, |
| "loss": 0.2941, |
| "mean_token_accuracy": 0.8985650539398193, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8418604651162791, |
| "grad_norm": 2.398179769515991, |
| "learning_rate": 9.15484992751095e-06, |
| "loss": 0.2971, |
| "mean_token_accuracy": 0.8980716466903687, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.8465116279069768, |
| "grad_norm": 2.3488447666168213, |
| "learning_rate": 9.140576474687263e-06, |
| "loss": 0.3054, |
| "mean_token_accuracy": 0.897182822227478, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.8511627906976744, |
| "grad_norm": 2.7520530223846436, |
| "learning_rate": 9.126196211632456e-06, |
| "loss": 0.3154, |
| "mean_token_accuracy": 0.8900938034057617, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.8558139534883721, |
| "grad_norm": 2.515666961669922, |
| "learning_rate": 9.11170956024653e-06, |
| "loss": 0.3116, |
| "mean_token_accuracy": 0.8922144770622253, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.8604651162790697, |
| "grad_norm": 2.2675559520721436, |
| "learning_rate": 9.097116945550794e-06, |
| "loss": 0.2906, |
| "mean_token_accuracy": 0.8984547257423401, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.8651162790697674, |
| "grad_norm": 2.3091530799865723, |
| "learning_rate": 9.082418795675397e-06, |
| "loss": 0.3165, |
| "mean_token_accuracy": 0.8925065398216248, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.8697674418604651, |
| "grad_norm": 2.641993284225464, |
| "learning_rate": 9.067615541846768e-06, |
| "loss": 0.2755, |
| "mean_token_accuracy": 0.8972795009613037, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.8744186046511628, |
| "grad_norm": 2.2171666622161865, |
| "learning_rate": 9.052707618374958e-06, |
| "loss": 0.2995, |
| "mean_token_accuracy": 0.8997421264648438, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.8790697674418605, |
| "grad_norm": 2.160520553588867, |
| "learning_rate": 9.037695462640908e-06, |
| "loss": 0.2758, |
| "mean_token_accuracy": 0.9074592590332031, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.8837209302325582, |
| "grad_norm": 2.49261212348938, |
| "learning_rate": 9.022579515083601e-06, |
| "loss": 0.2951, |
| "mean_token_accuracy": 0.8942018151283264, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8883720930232558, |
| "grad_norm": 2.5129523277282715, |
| "learning_rate": 9.007360219187163e-06, |
| "loss": 0.3419, |
| "mean_token_accuracy": 0.8804105520248413, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.8930232558139535, |
| "grad_norm": 2.299142360687256, |
| "learning_rate": 8.99203802146783e-06, |
| "loss": 0.254, |
| "mean_token_accuracy": 0.9106271862983704, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.8976744186046511, |
| "grad_norm": 2.291740655899048, |
| "learning_rate": 8.976613371460856e-06, |
| "loss": 0.3024, |
| "mean_token_accuracy": 0.8975442051887512, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.9023255813953488, |
| "grad_norm": 2.278927803039551, |
| "learning_rate": 8.961086721707331e-06, |
| "loss": 0.2812, |
| "mean_token_accuracy": 0.9085345268249512, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.9069767441860465, |
| "grad_norm": 2.2824349403381348, |
| "learning_rate": 8.945458527740892e-06, |
| "loss": 0.2813, |
| "mean_token_accuracy": 0.9089676141738892, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.9116279069767442, |
| "grad_norm": 2.3400731086730957, |
| "learning_rate": 8.929729248074364e-06, |
| "loss": 0.3127, |
| "mean_token_accuracy": 0.8936736583709717, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.9162790697674419, |
| "grad_norm": 2.4384615421295166, |
| "learning_rate": 8.913899344186312e-06, |
| "loss": 0.2703, |
| "mean_token_accuracy": 0.9109355211257935, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.9209302325581395, |
| "grad_norm": 2.4058189392089844, |
| "learning_rate": 8.897969280507494e-06, |
| "loss": 0.2786, |
| "mean_token_accuracy": 0.9076216816902161, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.9255813953488372, |
| "grad_norm": 2.4712047576904297, |
| "learning_rate": 8.881939524407238e-06, |
| "loss": 0.3093, |
| "mean_token_accuracy": 0.8929236531257629, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.9302325581395349, |
| "grad_norm": 2.4457972049713135, |
| "learning_rate": 8.86581054617973e-06, |
| "loss": 0.2869, |
| "mean_token_accuracy": 0.9015862345695496, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9348837209302325, |
| "grad_norm": 2.3394265174865723, |
| "learning_rate": 8.849582819030217e-06, |
| "loss": 0.3105, |
| "mean_token_accuracy": 0.8978766202926636, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.9395348837209302, |
| "grad_norm": 2.4344286918640137, |
| "learning_rate": 8.833256819061126e-06, |
| "loss": 0.2751, |
| "mean_token_accuracy": 0.9041284918785095, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.9441860465116279, |
| "grad_norm": 2.8893260955810547, |
| "learning_rate": 8.81683302525809e-06, |
| "loss": 0.2994, |
| "mean_token_accuracy": 0.8973665237426758, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.9488372093023256, |
| "grad_norm": 2.1813788414001465, |
| "learning_rate": 8.800311919475902e-06, |
| "loss": 0.2622, |
| "mean_token_accuracy": 0.9018022418022156, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.9534883720930233, |
| "grad_norm": 2.0994787216186523, |
| "learning_rate": 8.783693986424365e-06, |
| "loss": 0.2628, |
| "mean_token_accuracy": 0.9057013988494873, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.958139534883721, |
| "grad_norm": 2.2232422828674316, |
| "learning_rate": 8.76697971365409e-06, |
| "loss": 0.2909, |
| "mean_token_accuracy": 0.8990663290023804, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.9627906976744186, |
| "grad_norm": 2.5452654361724854, |
| "learning_rate": 8.750169591542177e-06, |
| "loss": 0.3163, |
| "mean_token_accuracy": 0.8898491859436035, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.9674418604651163, |
| "grad_norm": 2.470062017440796, |
| "learning_rate": 8.733264113277832e-06, |
| "loss": 0.2819, |
| "mean_token_accuracy": 0.9040852785110474, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.9720930232558139, |
| "grad_norm": 2.2468132972717285, |
| "learning_rate": 8.716263774847902e-06, |
| "loss": 0.2656, |
| "mean_token_accuracy": 0.9133898019790649, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.9767441860465116, |
| "grad_norm": 2.0833487510681152, |
| "learning_rate": 8.69916907502232e-06, |
| "loss": 0.2786, |
| "mean_token_accuracy": 0.9064552187919617, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9813953488372092, |
| "grad_norm": 2.21199369430542, |
| "learning_rate": 8.681980515339464e-06, |
| "loss": 0.2723, |
| "mean_token_accuracy": 0.906145453453064, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.986046511627907, |
| "grad_norm": 2.214639663696289, |
| "learning_rate": 8.664698600091462e-06, |
| "loss": 0.2998, |
| "mean_token_accuracy": 0.897372841835022, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.9906976744186047, |
| "grad_norm": 2.201284408569336, |
| "learning_rate": 8.64732383630937e-06, |
| "loss": 0.2632, |
| "mean_token_accuracy": 0.9081220030784607, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.9953488372093023, |
| "grad_norm": 2.226452112197876, |
| "learning_rate": 8.629856733748325e-06, |
| "loss": 0.3033, |
| "mean_token_accuracy": 0.8968695402145386, |
| "step": 214 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.1136155128479004, |
| "learning_rate": 8.612297804872562e-06, |
| "loss": 0.2636, |
| "mean_token_accuracy": 0.9030256271362305, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.0046511627906978, |
| "grad_norm": 3.3606746196746826, |
| "learning_rate": 8.594647564840407e-06, |
| "loss": 0.1513, |
| "mean_token_accuracy": 0.9528185129165649, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.0093023255813953, |
| "grad_norm": 2.7589690685272217, |
| "learning_rate": 8.57690653148913e-06, |
| "loss": 0.1725, |
| "mean_token_accuracy": 0.938120424747467, |
| "step": 217 |
| }, |
| { |
| "epoch": 1.013953488372093, |
| "grad_norm": 2.593282461166382, |
| "learning_rate": 8.559075225319786e-06, |
| "loss": 0.1453, |
| "mean_token_accuracy": 0.9510069489479065, |
| "step": 218 |
| }, |
| { |
| "epoch": 1.0186046511627906, |
| "grad_norm": 2.1907403469085693, |
| "learning_rate": 8.54115416948192e-06, |
| "loss": 0.1453, |
| "mean_token_accuracy": 0.9506734013557434, |
| "step": 219 |
| }, |
| { |
| "epoch": 1.0232558139534884, |
| "grad_norm": 2.0132081508636475, |
| "learning_rate": 8.523143889758228e-06, |
| "loss": 0.1195, |
| "mean_token_accuracy": 0.9594102501869202, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.027906976744186, |
| "grad_norm": 1.8184553384780884, |
| "learning_rate": 8.505044914549131e-06, |
| "loss": 0.1504, |
| "mean_token_accuracy": 0.945387601852417, |
| "step": 221 |
| }, |
| { |
| "epoch": 1.0325581395348837, |
| "grad_norm": 2.0166773796081543, |
| "learning_rate": 8.48685777485727e-06, |
| "loss": 0.1271, |
| "mean_token_accuracy": 0.95333331823349, |
| "step": 222 |
| }, |
| { |
| "epoch": 1.0372093023255813, |
| "grad_norm": 2.1910595893859863, |
| "learning_rate": 8.46858300427193e-06, |
| "loss": 0.1377, |
| "mean_token_accuracy": 0.954576849937439, |
| "step": 223 |
| }, |
| { |
| "epoch": 1.041860465116279, |
| "grad_norm": 2.6961281299591064, |
| "learning_rate": 8.450221138953383e-06, |
| "loss": 0.128, |
| "mean_token_accuracy": 0.951163649559021, |
| "step": 224 |
| }, |
| { |
| "epoch": 1.0465116279069768, |
| "grad_norm": 2.3894295692443848, |
| "learning_rate": 8.431772717617154e-06, |
| "loss": 0.1398, |
| "mean_token_accuracy": 0.9508081674575806, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.0511627906976744, |
| "grad_norm": 2.134735345840454, |
| "learning_rate": 8.413238281518225e-06, |
| "loss": 0.1235, |
| "mean_token_accuracy": 0.9533866047859192, |
| "step": 226 |
| }, |
| { |
| "epoch": 1.0558139534883721, |
| "grad_norm": 2.099576711654663, |
| "learning_rate": 8.394618374435148e-06, |
| "loss": 0.1474, |
| "mean_token_accuracy": 0.9495023488998413, |
| "step": 227 |
| }, |
| { |
| "epoch": 1.0604651162790697, |
| "grad_norm": 2.013437509536743, |
| "learning_rate": 8.375913542654093e-06, |
| "loss": 0.1406, |
| "mean_token_accuracy": 0.9510268568992615, |
| "step": 228 |
| }, |
| { |
| "epoch": 1.0651162790697675, |
| "grad_norm": 2.3148350715637207, |
| "learning_rate": 8.357124334952818e-06, |
| "loss": 0.1454, |
| "mean_token_accuracy": 0.9502067565917969, |
| "step": 229 |
| }, |
| { |
| "epoch": 1.069767441860465, |
| "grad_norm": 1.961985468864441, |
| "learning_rate": 8.33825130258458e-06, |
| "loss": 0.1278, |
| "mean_token_accuracy": 0.9549334645271301, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.0744186046511628, |
| "grad_norm": 1.8867031335830688, |
| "learning_rate": 8.319294999261941e-06, |
| "loss": 0.1226, |
| "mean_token_accuracy": 0.9560340046882629, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.0790697674418606, |
| "grad_norm": 1.8320002555847168, |
| "learning_rate": 8.300255981140544e-06, |
| "loss": 0.1202, |
| "mean_token_accuracy": 0.9573019742965698, |
| "step": 232 |
| }, |
| { |
| "epoch": 1.083720930232558, |
| "grad_norm": 2.1686620712280273, |
| "learning_rate": 8.281134806802783e-06, |
| "loss": 0.1502, |
| "mean_token_accuracy": 0.9432587027549744, |
| "step": 233 |
| }, |
| { |
| "epoch": 1.0883720930232559, |
| "grad_norm": 1.9972004890441895, |
| "learning_rate": 8.261932037241418e-06, |
| "loss": 0.1627, |
| "mean_token_accuracy": 0.94051593542099, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.0930232558139534, |
| "grad_norm": 2.0510964393615723, |
| "learning_rate": 8.242648235843123e-06, |
| "loss": 0.1557, |
| "mean_token_accuracy": 0.9502580761909485, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.0976744186046512, |
| "grad_norm": 1.992247462272644, |
| "learning_rate": 8.223283968371945e-06, |
| "loss": 0.1296, |
| "mean_token_accuracy": 0.9547486305236816, |
| "step": 236 |
| }, |
| { |
| "epoch": 1.1023255813953488, |
| "grad_norm": 2.0515332221984863, |
| "learning_rate": 8.203839802952708e-06, |
| "loss": 0.1311, |
| "mean_token_accuracy": 0.9554937481880188, |
| "step": 237 |
| }, |
| { |
| "epoch": 1.1069767441860465, |
| "grad_norm": 1.8534224033355713, |
| "learning_rate": 8.184316310054355e-06, |
| "loss": 0.1354, |
| "mean_token_accuracy": 0.9514824748039246, |
| "step": 238 |
| }, |
| { |
| "epoch": 1.1116279069767443, |
| "grad_norm": 2.0729804039001465, |
| "learning_rate": 8.164714062473201e-06, |
| "loss": 0.1397, |
| "mean_token_accuracy": 0.9531170129776001, |
| "step": 239 |
| }, |
| { |
| "epoch": 1.1162790697674418, |
| "grad_norm": 1.9124263525009155, |
| "learning_rate": 8.14503363531613e-06, |
| "loss": 0.1197, |
| "mean_token_accuracy": 0.9569715857505798, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.1209302325581396, |
| "grad_norm": 1.9606989622116089, |
| "learning_rate": 8.125275605983725e-06, |
| "loss": 0.1273, |
| "mean_token_accuracy": 0.9557822942733765, |
| "step": 241 |
| }, |
| { |
| "epoch": 1.1255813953488372, |
| "grad_norm": 2.081315755844116, |
| "learning_rate": 8.10544055415332e-06, |
| "loss": 0.1401, |
| "mean_token_accuracy": 0.9516574740409851, |
| "step": 242 |
| }, |
| { |
| "epoch": 1.130232558139535, |
| "grad_norm": 1.9782904386520386, |
| "learning_rate": 8.085529061762007e-06, |
| "loss": 0.1328, |
| "mean_token_accuracy": 0.9561711549758911, |
| "step": 243 |
| }, |
| { |
| "epoch": 1.1348837209302325, |
| "grad_norm": 2.144768238067627, |
| "learning_rate": 8.065541712989546e-06, |
| "loss": 0.1337, |
| "mean_token_accuracy": 0.9531194567680359, |
| "step": 244 |
| }, |
| { |
| "epoch": 1.1395348837209303, |
| "grad_norm": 1.9130630493164062, |
| "learning_rate": 8.04547909424124e-06, |
| "loss": 0.1402, |
| "mean_token_accuracy": 0.9525547623634338, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.1441860465116278, |
| "grad_norm": 2.034174919128418, |
| "learning_rate": 8.025341794130722e-06, |
| "loss": 0.1402, |
| "mean_token_accuracy": 0.947668731212616, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.1488372093023256, |
| "grad_norm": 1.8769278526306152, |
| "learning_rate": 8.005130403462687e-06, |
| "loss": 0.12, |
| "mean_token_accuracy": 0.9560899138450623, |
| "step": 247 |
| }, |
| { |
| "epoch": 1.1534883720930234, |
| "grad_norm": 1.8356506824493408, |
| "learning_rate": 7.98484551521556e-06, |
| "loss": 0.1351, |
| "mean_token_accuracy": 0.9524879455566406, |
| "step": 248 |
| }, |
| { |
| "epoch": 1.158139534883721, |
| "grad_norm": 2.1841554641723633, |
| "learning_rate": 7.964487724524105e-06, |
| "loss": 0.1522, |
| "mean_token_accuracy": 0.9461566209793091, |
| "step": 249 |
| }, |
| { |
| "epoch": 1.1627906976744187, |
| "grad_norm": 1.7897896766662598, |
| "learning_rate": 7.944057628661948e-06, |
| "loss": 0.1304, |
| "mean_token_accuracy": 0.9538383483886719, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.1674418604651162, |
| "grad_norm": 1.7146762609481812, |
| "learning_rate": 7.923555827024069e-06, |
| "loss": 0.1236, |
| "mean_token_accuracy": 0.9551189541816711, |
| "step": 251 |
| }, |
| { |
| "epoch": 1.172093023255814, |
| "grad_norm": 1.9337011575698853, |
| "learning_rate": 7.902982921109215e-06, |
| "loss": 0.1395, |
| "mean_token_accuracy": 0.950564980506897, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.1767441860465115, |
| "grad_norm": 2.312887668609619, |
| "learning_rate": 7.882339514502236e-06, |
| "loss": 0.1599, |
| "mean_token_accuracy": 0.9496940970420837, |
| "step": 253 |
| }, |
| { |
| "epoch": 1.1813953488372093, |
| "grad_norm": 2.0187339782714844, |
| "learning_rate": 7.861626212856404e-06, |
| "loss": 0.1197, |
| "mean_token_accuracy": 0.9586181640625, |
| "step": 254 |
| }, |
| { |
| "epoch": 1.1860465116279069, |
| "grad_norm": 1.9361454248428345, |
| "learning_rate": 7.840843623875621e-06, |
| "loss": 0.1398, |
| "mean_token_accuracy": 0.9482730031013489, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.1906976744186046, |
| "grad_norm": 1.932745099067688, |
| "learning_rate": 7.8199923572966e-06, |
| "loss": 0.137, |
| "mean_token_accuracy": 0.9541915655136108, |
| "step": 256 |
| }, |
| { |
| "epoch": 1.1953488372093024, |
| "grad_norm": 1.8732504844665527, |
| "learning_rate": 7.799073024870972e-06, |
| "loss": 0.1311, |
| "mean_token_accuracy": 0.9530263543128967, |
| "step": 257 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 1.8641448020935059, |
| "learning_rate": 7.778086240347343e-06, |
| "loss": 0.1301, |
| "mean_token_accuracy": 0.9536779522895813, |
| "step": 258 |
| }, |
| { |
| "epoch": 1.2046511627906977, |
| "grad_norm": 1.8090254068374634, |
| "learning_rate": 7.757032619453285e-06, |
| "loss": 0.1179, |
| "mean_token_accuracy": 0.9588613510131836, |
| "step": 259 |
| }, |
| { |
| "epoch": 1.2093023255813953, |
| "grad_norm": 1.9466335773468018, |
| "learning_rate": 7.735912779877266e-06, |
| "loss": 0.1432, |
| "mean_token_accuracy": 0.9497014880180359, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.213953488372093, |
| "grad_norm": 2.1102936267852783, |
| "learning_rate": 7.714727341250533e-06, |
| "loss": 0.1516, |
| "mean_token_accuracy": 0.9480257034301758, |
| "step": 261 |
| }, |
| { |
| "epoch": 1.2186046511627908, |
| "grad_norm": 1.830043911933899, |
| "learning_rate": 7.693476925128937e-06, |
| "loss": 0.1471, |
| "mean_token_accuracy": 0.9475498795509338, |
| "step": 262 |
| }, |
| { |
| "epoch": 1.2232558139534884, |
| "grad_norm": 1.9706553220748901, |
| "learning_rate": 7.672162154974686e-06, |
| "loss": 0.1441, |
| "mean_token_accuracy": 0.9502365589141846, |
| "step": 263 |
| }, |
| { |
| "epoch": 1.2279069767441861, |
| "grad_norm": 1.7491787672042847, |
| "learning_rate": 7.650783656138065e-06, |
| "loss": 0.1379, |
| "mean_token_accuracy": 0.9508991241455078, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.2325581395348837, |
| "grad_norm": 1.9815034866333008, |
| "learning_rate": 7.629342055839077e-06, |
| "loss": 0.1638, |
| "mean_token_accuracy": 0.9426482915878296, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.2372093023255815, |
| "grad_norm": 2.0385522842407227, |
| "learning_rate": 7.607837983149057e-06, |
| "loss": 0.1593, |
| "mean_token_accuracy": 0.9459502696990967, |
| "step": 266 |
| }, |
| { |
| "epoch": 1.241860465116279, |
| "grad_norm": 2.1366653442382812, |
| "learning_rate": 7.586272068972196e-06, |
| "loss": 0.1831, |
| "mean_token_accuracy": 0.9355138540267944, |
| "step": 267 |
| }, |
| { |
| "epoch": 1.2465116279069768, |
| "grad_norm": 1.7888002395629883, |
| "learning_rate": 7.564644946027049e-06, |
| "loss": 0.1226, |
| "mean_token_accuracy": 0.9529392123222351, |
| "step": 268 |
| }, |
| { |
| "epoch": 1.2511627906976743, |
| "grad_norm": 2.0460989475250244, |
| "learning_rate": 7.5429572488279615e-06, |
| "loss": 0.1344, |
| "mean_token_accuracy": 0.9502557516098022, |
| "step": 269 |
| }, |
| { |
| "epoch": 1.255813953488372, |
| "grad_norm": 1.8217569589614868, |
| "learning_rate": 7.521209613666457e-06, |
| "loss": 0.1224, |
| "mean_token_accuracy": 0.9609270095825195, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.2604651162790699, |
| "grad_norm": 1.8216779232025146, |
| "learning_rate": 7.499402678592568e-06, |
| "loss": 0.1362, |
| "mean_token_accuracy": 0.9506351351737976, |
| "step": 271 |
| }, |
| { |
| "epoch": 1.2651162790697674, |
| "grad_norm": 1.7524104118347168, |
| "learning_rate": 7.477537083396114e-06, |
| "loss": 0.1204, |
| "mean_token_accuracy": 0.9553118348121643, |
| "step": 272 |
| }, |
| { |
| "epoch": 1.2697674418604652, |
| "grad_norm": 1.975805640220642, |
| "learning_rate": 7.45561346958794e-06, |
| "loss": 0.1201, |
| "mean_token_accuracy": 0.9567315578460693, |
| "step": 273 |
| }, |
| { |
| "epoch": 1.2744186046511627, |
| "grad_norm": 1.6656185388565063, |
| "learning_rate": 7.433632480381083e-06, |
| "loss": 0.1097, |
| "mean_token_accuracy": 0.9608015418052673, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.2790697674418605, |
| "grad_norm": 1.9660391807556152, |
| "learning_rate": 7.4115947606719105e-06, |
| "loss": 0.136, |
| "mean_token_accuracy": 0.9484320282936096, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.283720930232558, |
| "grad_norm": 1.9652019739151, |
| "learning_rate": 7.389500957021192e-06, |
| "loss": 0.1188, |
| "mean_token_accuracy": 0.9587832689285278, |
| "step": 276 |
| }, |
| { |
| "epoch": 1.2883720930232558, |
| "grad_norm": 2.1324007511138916, |
| "learning_rate": 7.367351717635136e-06, |
| "loss": 0.1426, |
| "mean_token_accuracy": 0.9486826062202454, |
| "step": 277 |
| }, |
| { |
| "epoch": 1.2930232558139534, |
| "grad_norm": 2.0965774059295654, |
| "learning_rate": 7.345147692346373e-06, |
| "loss": 0.1353, |
| "mean_token_accuracy": 0.9534883499145508, |
| "step": 278 |
| }, |
| { |
| "epoch": 1.2976744186046512, |
| "grad_norm": 1.8807930946350098, |
| "learning_rate": 7.3228895325948835e-06, |
| "loss": 0.1245, |
| "mean_token_accuracy": 0.9569152593612671, |
| "step": 279 |
| }, |
| { |
| "epoch": 1.302325581395349, |
| "grad_norm": 1.9116649627685547, |
| "learning_rate": 7.3005778914088895e-06, |
| "loss": 0.1232, |
| "mean_token_accuracy": 0.9569117426872253, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.3069767441860465, |
| "grad_norm": 2.0371623039245605, |
| "learning_rate": 7.278213423385701e-06, |
| "loss": 0.146, |
| "mean_token_accuracy": 0.9478211998939514, |
| "step": 281 |
| }, |
| { |
| "epoch": 1.3116279069767443, |
| "grad_norm": 2.396204710006714, |
| "learning_rate": 7.255796784672496e-06, |
| "loss": 0.1844, |
| "mean_token_accuracy": 0.9387242794036865, |
| "step": 282 |
| }, |
| { |
| "epoch": 1.3162790697674418, |
| "grad_norm": 1.8520818948745728, |
| "learning_rate": 7.233328632947087e-06, |
| "loss": 0.1248, |
| "mean_token_accuracy": 0.9575390219688416, |
| "step": 283 |
| }, |
| { |
| "epoch": 1.3209302325581396, |
| "grad_norm": 4.048036575317383, |
| "learning_rate": 7.210809627398615e-06, |
| "loss": 0.1537, |
| "mean_token_accuracy": 0.9447412490844727, |
| "step": 284 |
| }, |
| { |
| "epoch": 1.3255813953488373, |
| "grad_norm": 1.67165207862854, |
| "learning_rate": 7.188240428708211e-06, |
| "loss": 0.1078, |
| "mean_token_accuracy": 0.9622266292572021, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.330232558139535, |
| "grad_norm": 1.8730194568634033, |
| "learning_rate": 7.165621699029615e-06, |
| "loss": 0.1453, |
| "mean_token_accuracy": 0.9500071406364441, |
| "step": 286 |
| }, |
| { |
| "epoch": 1.3348837209302324, |
| "grad_norm": 1.767138123512268, |
| "learning_rate": 7.1429541019697505e-06, |
| "loss": 0.1418, |
| "mean_token_accuracy": 0.9493996500968933, |
| "step": 287 |
| }, |
| { |
| "epoch": 1.3395348837209302, |
| "grad_norm": 2.1134703159332275, |
| "learning_rate": 7.120238302569245e-06, |
| "loss": 0.1547, |
| "mean_token_accuracy": 0.9479333758354187, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.344186046511628, |
| "grad_norm": 2.0318989753723145, |
| "learning_rate": 7.097474967282936e-06, |
| "loss": 0.1399, |
| "mean_token_accuracy": 0.9505158066749573, |
| "step": 289 |
| }, |
| { |
| "epoch": 1.3488372093023255, |
| "grad_norm": 2.1438822746276855, |
| "learning_rate": 7.0746647639602994e-06, |
| "loss": 0.146, |
| "mean_token_accuracy": 0.9493649005889893, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.3534883720930233, |
| "grad_norm": 2.045762777328491, |
| "learning_rate": 7.051808361825867e-06, |
| "loss": 0.1546, |
| "mean_token_accuracy": 0.9482935070991516, |
| "step": 291 |
| }, |
| { |
| "epoch": 1.3581395348837209, |
| "grad_norm": 2.4444692134857178, |
| "learning_rate": 7.028906431459593e-06, |
| "loss": 0.163, |
| "mean_token_accuracy": 0.9413919448852539, |
| "step": 292 |
| }, |
| { |
| "epoch": 1.3627906976744186, |
| "grad_norm": 2.065103769302368, |
| "learning_rate": 7.0059596447771714e-06, |
| "loss": 0.1445, |
| "mean_token_accuracy": 0.9467507600784302, |
| "step": 293 |
| }, |
| { |
| "epoch": 1.3674418604651164, |
| "grad_norm": 1.9953572750091553, |
| "learning_rate": 6.982968675010332e-06, |
| "loss": 0.1237, |
| "mean_token_accuracy": 0.9579423666000366, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.372093023255814, |
| "grad_norm": 1.9525924921035767, |
| "learning_rate": 6.959934196687079e-06, |
| "loss": 0.1462, |
| "mean_token_accuracy": 0.9512315988540649, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.3767441860465115, |
| "grad_norm": 2.0204193592071533, |
| "learning_rate": 6.93685688561191e-06, |
| "loss": 0.147, |
| "mean_token_accuracy": 0.9485055804252625, |
| "step": 296 |
| }, |
| { |
| "epoch": 1.3813953488372093, |
| "grad_norm": 2.029042959213257, |
| "learning_rate": 6.913737418845985e-06, |
| "loss": 0.1403, |
| "mean_token_accuracy": 0.9497275352478027, |
| "step": 297 |
| }, |
| { |
| "epoch": 1.386046511627907, |
| "grad_norm": 1.9784486293792725, |
| "learning_rate": 6.890576474687264e-06, |
| "loss": 0.1365, |
| "mean_token_accuracy": 0.9519021511077881, |
| "step": 298 |
| }, |
| { |
| "epoch": 1.3906976744186046, |
| "grad_norm": 1.9087692499160767, |
| "learning_rate": 6.8673747326506e-06, |
| "loss": 0.1382, |
| "mean_token_accuracy": 0.9500246644020081, |
| "step": 299 |
| }, |
| { |
| "epoch": 1.3953488372093024, |
| "grad_norm": 1.8645182847976685, |
| "learning_rate": 6.8441328734478115e-06, |
| "loss": 0.133, |
| "mean_token_accuracy": 0.9523329734802246, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 1.7279090881347656, |
| "learning_rate": 6.820851578967708e-06, |
| "loss": 0.1288, |
| "mean_token_accuracy": 0.9540249109268188, |
| "step": 301 |
| }, |
| { |
| "epoch": 1.4046511627906977, |
| "grad_norm": 1.8317281007766724, |
| "learning_rate": 6.797531532256079e-06, |
| "loss": 0.1435, |
| "mean_token_accuracy": 0.947135865688324, |
| "step": 302 |
| }, |
| { |
| "epoch": 1.4093023255813955, |
| "grad_norm": 1.9698084592819214, |
| "learning_rate": 6.774173417495667e-06, |
| "loss": 0.1512, |
| "mean_token_accuracy": 0.9412643313407898, |
| "step": 303 |
| }, |
| { |
| "epoch": 1.413953488372093, |
| "grad_norm": 1.7703008651733398, |
| "learning_rate": 6.750777919986075e-06, |
| "loss": 0.1383, |
| "mean_token_accuracy": 0.9496229290962219, |
| "step": 304 |
| }, |
| { |
| "epoch": 1.4186046511627908, |
| "grad_norm": 1.9811159372329712, |
| "learning_rate": 6.727345726123684e-06, |
| "loss": 0.1715, |
| "mean_token_accuracy": 0.9391480684280396, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.4232558139534883, |
| "grad_norm": 1.7490876913070679, |
| "learning_rate": 6.703877523381495e-06, |
| "loss": 0.1267, |
| "mean_token_accuracy": 0.9528796076774597, |
| "step": 306 |
| }, |
| { |
| "epoch": 1.427906976744186, |
| "grad_norm": 1.9982609748840332, |
| "learning_rate": 6.680374000288968e-06, |
| "loss": 0.1325, |
| "mean_token_accuracy": 0.9569318890571594, |
| "step": 307 |
| }, |
| { |
| "epoch": 1.4325581395348836, |
| "grad_norm": 1.940192461013794, |
| "learning_rate": 6.656835846411824e-06, |
| "loss": 0.1466, |
| "mean_token_accuracy": 0.9504638314247131, |
| "step": 308 |
| }, |
| { |
| "epoch": 1.4372093023255814, |
| "grad_norm": 2.010435104370117, |
| "learning_rate": 6.633263752331808e-06, |
| "loss": 0.1462, |
| "mean_token_accuracy": 0.9526048302650452, |
| "step": 309 |
| }, |
| { |
| "epoch": 1.441860465116279, |
| "grad_norm": 1.848711371421814, |
| "learning_rate": 6.609658409626431e-06, |
| "loss": 0.1356, |
| "mean_token_accuracy": 0.9486258625984192, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.4465116279069767, |
| "grad_norm": 1.9631938934326172, |
| "learning_rate": 6.586020510848676e-06, |
| "loss": 0.1161, |
| "mean_token_accuracy": 0.9588515162467957, |
| "step": 311 |
| }, |
| { |
| "epoch": 1.4511627906976745, |
| "grad_norm": 2.154928207397461, |
| "learning_rate": 6.562350749506691e-06, |
| "loss": 0.1685, |
| "mean_token_accuracy": 0.9434839487075806, |
| "step": 312 |
| }, |
| { |
| "epoch": 1.455813953488372, |
| "grad_norm": 1.8358088731765747, |
| "learning_rate": 6.538649820043427e-06, |
| "loss": 0.1409, |
| "mean_token_accuracy": 0.9509722590446472, |
| "step": 313 |
| }, |
| { |
| "epoch": 1.4604651162790698, |
| "grad_norm": 1.9285755157470703, |
| "learning_rate": 6.514918417816275e-06, |
| "loss": 0.1319, |
| "mean_token_accuracy": 0.9517412781715393, |
| "step": 314 |
| }, |
| { |
| "epoch": 1.4651162790697674, |
| "grad_norm": 1.847544550895691, |
| "learning_rate": 6.4911572390766575e-06, |
| "loss": 0.1345, |
| "mean_token_accuracy": 0.9501661062240601, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.4697674418604652, |
| "grad_norm": 2.1781485080718994, |
| "learning_rate": 6.46736698094961e-06, |
| "loss": 0.165, |
| "mean_token_accuracy": 0.9442425966262817, |
| "step": 316 |
| }, |
| { |
| "epoch": 1.474418604651163, |
| "grad_norm": 2.6374707221984863, |
| "learning_rate": 6.443548341413316e-06, |
| "loss": 0.1405, |
| "mean_token_accuracy": 0.948967695236206, |
| "step": 317 |
| }, |
| { |
| "epoch": 1.4790697674418605, |
| "grad_norm": 1.8847520351409912, |
| "learning_rate": 6.419702019278643e-06, |
| "loss": 0.1415, |
| "mean_token_accuracy": 0.9527637958526611, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.483720930232558, |
| "grad_norm": 2.0058882236480713, |
| "learning_rate": 6.3958287141686294e-06, |
| "loss": 0.1419, |
| "mean_token_accuracy": 0.948972225189209, |
| "step": 319 |
| }, |
| { |
| "epoch": 1.4883720930232558, |
| "grad_norm": 1.837763786315918, |
| "learning_rate": 6.371929126497963e-06, |
| "loss": 0.119, |
| "mean_token_accuracy": 0.9574694037437439, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.4930232558139536, |
| "grad_norm": 1.9148606061935425, |
| "learning_rate": 6.348003957452433e-06, |
| "loss": 0.1352, |
| "mean_token_accuracy": 0.9492248296737671, |
| "step": 321 |
| }, |
| { |
| "epoch": 1.4976744186046511, |
| "grad_norm": 1.9753315448760986, |
| "learning_rate": 6.324053908968353e-06, |
| "loss": 0.1364, |
| "mean_token_accuracy": 0.9513832330703735, |
| "step": 322 |
| }, |
| { |
| "epoch": 1.5023255813953489, |
| "grad_norm": 1.8429263830184937, |
| "learning_rate": 6.300079683711973e-06, |
| "loss": 0.1237, |
| "mean_token_accuracy": 0.9562457203865051, |
| "step": 323 |
| }, |
| { |
| "epoch": 1.5069767441860464, |
| "grad_norm": 1.7931606769561768, |
| "learning_rate": 6.276081985058857e-06, |
| "loss": 0.1089, |
| "mean_token_accuracy": 0.9609548449516296, |
| "step": 324 |
| }, |
| { |
| "epoch": 1.5116279069767442, |
| "grad_norm": 1.9909682273864746, |
| "learning_rate": 6.2520615170732555e-06, |
| "loss": 0.1365, |
| "mean_token_accuracy": 0.9544373154640198, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.516279069767442, |
| "grad_norm": 2.083770990371704, |
| "learning_rate": 6.228018984487443e-06, |
| "loss": 0.1527, |
| "mean_token_accuracy": 0.9463026523590088, |
| "step": 326 |
| }, |
| { |
| "epoch": 1.5209302325581395, |
| "grad_norm": 2.060635805130005, |
| "learning_rate": 6.20395509268104e-06, |
| "loss": 0.1416, |
| "mean_token_accuracy": 0.9506000876426697, |
| "step": 327 |
| }, |
| { |
| "epoch": 1.525581395348837, |
| "grad_norm": 2.266390323638916, |
| "learning_rate": 6.179870547660326e-06, |
| "loss": 0.1769, |
| "mean_token_accuracy": 0.9442271590232849, |
| "step": 328 |
| }, |
| { |
| "epoch": 1.5302325581395348, |
| "grad_norm": 1.9692381620407104, |
| "learning_rate": 6.15576605603752e-06, |
| "loss": 0.1344, |
| "mean_token_accuracy": 0.9521507024765015, |
| "step": 329 |
| }, |
| { |
| "epoch": 1.5348837209302326, |
| "grad_norm": 1.6992781162261963, |
| "learning_rate": 6.13164232501005e-06, |
| "loss": 0.1169, |
| "mean_token_accuracy": 0.9589894413948059, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.5395348837209304, |
| "grad_norm": 1.78009831905365, |
| "learning_rate": 6.107500062339806e-06, |
| "loss": 0.1232, |
| "mean_token_accuracy": 0.9531930088996887, |
| "step": 331 |
| }, |
| { |
| "epoch": 1.544186046511628, |
| "grad_norm": 1.8769017457962036, |
| "learning_rate": 6.083339976332375e-06, |
| "loss": 0.1308, |
| "mean_token_accuracy": 0.9528769850730896, |
| "step": 332 |
| }, |
| { |
| "epoch": 1.5488372093023255, |
| "grad_norm": 1.9236352443695068, |
| "learning_rate": 6.05916277581626e-06, |
| "loss": 0.1425, |
| "mean_token_accuracy": 0.9482171535491943, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.5534883720930233, |
| "grad_norm": 1.9040541648864746, |
| "learning_rate": 6.034969170122079e-06, |
| "loss": 0.1294, |
| "mean_token_accuracy": 0.9605388045310974, |
| "step": 334 |
| }, |
| { |
| "epoch": 1.558139534883721, |
| "grad_norm": 1.9620603322982788, |
| "learning_rate": 6.010759869061768e-06, |
| "loss": 0.1617, |
| "mean_token_accuracy": 0.9422249794006348, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.5627906976744186, |
| "grad_norm": 1.784496784210205, |
| "learning_rate": 5.986535582907739e-06, |
| "loss": 0.1198, |
| "mean_token_accuracy": 0.957058310508728, |
| "step": 336 |
| }, |
| { |
| "epoch": 1.5674418604651161, |
| "grad_norm": 1.819798231124878, |
| "learning_rate": 5.96229702237205e-06, |
| "loss": 0.1157, |
| "mean_token_accuracy": 0.9596412777900696, |
| "step": 337 |
| }, |
| { |
| "epoch": 1.572093023255814, |
| "grad_norm": 1.9021272659301758, |
| "learning_rate": 5.938044898585555e-06, |
| "loss": 0.1374, |
| "mean_token_accuracy": 0.9488742351531982, |
| "step": 338 |
| }, |
| { |
| "epoch": 1.5767441860465117, |
| "grad_norm": 1.9908572435379028, |
| "learning_rate": 5.913779923077035e-06, |
| "loss": 0.1597, |
| "mean_token_accuracy": 0.9456487894058228, |
| "step": 339 |
| }, |
| { |
| "epoch": 1.5813953488372094, |
| "grad_norm": 1.9344072341918945, |
| "learning_rate": 5.889502807752329e-06, |
| "loss": 0.152, |
| "mean_token_accuracy": 0.9439780712127686, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.586046511627907, |
| "grad_norm": 1.9438843727111816, |
| "learning_rate": 5.865214264873441e-06, |
| "loss": 0.1355, |
| "mean_token_accuracy": 0.9536268711090088, |
| "step": 341 |
| }, |
| { |
| "epoch": 1.5906976744186045, |
| "grad_norm": 1.8337723016738892, |
| "learning_rate": 5.840915007037648e-06, |
| "loss": 0.1248, |
| "mean_token_accuracy": 0.9561098217964172, |
| "step": 342 |
| }, |
| { |
| "epoch": 1.5953488372093023, |
| "grad_norm": 2.127720594406128, |
| "learning_rate": 5.816605747156588e-06, |
| "loss": 0.1514, |
| "mean_token_accuracy": 0.9452188014984131, |
| "step": 343 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 1.8010351657867432, |
| "learning_rate": 5.792287198435349e-06, |
| "loss": 0.1372, |
| "mean_token_accuracy": 0.9540988802909851, |
| "step": 344 |
| }, |
| { |
| "epoch": 1.6046511627906976, |
| "grad_norm": 1.8526756763458252, |
| "learning_rate": 5.767960074351545e-06, |
| "loss": 0.1394, |
| "mean_token_accuracy": 0.953599214553833, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.6093023255813952, |
| "grad_norm": 1.8736450672149658, |
| "learning_rate": 5.74362508863438e-06, |
| "loss": 0.1274, |
| "mean_token_accuracy": 0.953865110874176, |
| "step": 346 |
| }, |
| { |
| "epoch": 1.613953488372093, |
| "grad_norm": 2.073957920074463, |
| "learning_rate": 5.719282955243705e-06, |
| "loss": 0.1559, |
| "mean_token_accuracy": 0.9409741163253784, |
| "step": 347 |
| }, |
| { |
| "epoch": 1.6186046511627907, |
| "grad_norm": 2.255732536315918, |
| "learning_rate": 5.69493438834908e-06, |
| "loss": 0.1601, |
| "mean_token_accuracy": 0.9462425708770752, |
| "step": 348 |
| }, |
| { |
| "epoch": 1.6232558139534885, |
| "grad_norm": 2.0009047985076904, |
| "learning_rate": 5.670580102308816e-06, |
| "loss": 0.1326, |
| "mean_token_accuracy": 0.9542755484580994, |
| "step": 349 |
| }, |
| { |
| "epoch": 1.627906976744186, |
| "grad_norm": 1.8203014135360718, |
| "learning_rate": 5.646220811649013e-06, |
| "loss": 0.1201, |
| "mean_token_accuracy": 0.9584925174713135, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.6325581395348836, |
| "grad_norm": 2.1540281772613525, |
| "learning_rate": 5.6218572310426065e-06, |
| "loss": 0.1561, |
| "mean_token_accuracy": 0.9470699429512024, |
| "step": 351 |
| }, |
| { |
| "epoch": 1.6372093023255814, |
| "grad_norm": 1.8674291372299194, |
| "learning_rate": 5.59749007528839e-06, |
| "loss": 0.1381, |
| "mean_token_accuracy": 0.9516509175300598, |
| "step": 352 |
| }, |
| { |
| "epoch": 1.6418604651162791, |
| "grad_norm": 1.9634373188018799, |
| "learning_rate": 5.573120059290047e-06, |
| "loss": 0.142, |
| "mean_token_accuracy": 0.9484654664993286, |
| "step": 353 |
| }, |
| { |
| "epoch": 1.6465116279069767, |
| "grad_norm": 1.9212641716003418, |
| "learning_rate": 5.5487478980351805e-06, |
| "loss": 0.1452, |
| "mean_token_accuracy": 0.9457268714904785, |
| "step": 354 |
| }, |
| { |
| "epoch": 1.6511627906976745, |
| "grad_norm": 1.8786492347717285, |
| "learning_rate": 5.524374306574331e-06, |
| "loss": 0.1186, |
| "mean_token_accuracy": 0.9576781392097473, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.655813953488372, |
| "grad_norm": 1.8229862451553345, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.1398, |
| "mean_token_accuracy": 0.9506021738052368, |
| "step": 356 |
| }, |
| { |
| "epoch": 1.6604651162790698, |
| "grad_norm": 1.99154531955719, |
| "learning_rate": 5.47562569342567e-06, |
| "loss": 0.1332, |
| "mean_token_accuracy": 0.9508275985717773, |
| "step": 357 |
| }, |
| { |
| "epoch": 1.6651162790697676, |
| "grad_norm": 1.8731307983398438, |
| "learning_rate": 5.451252101964821e-06, |
| "loss": 0.1318, |
| "mean_token_accuracy": 0.9521738886833191, |
| "step": 358 |
| }, |
| { |
| "epoch": 1.669767441860465, |
| "grad_norm": 2.3059403896331787, |
| "learning_rate": 5.426879940709956e-06, |
| "loss": 0.1782, |
| "mean_token_accuracy": 0.9378255605697632, |
| "step": 359 |
| }, |
| { |
| "epoch": 1.6744186046511627, |
| "grad_norm": 1.8346630334854126, |
| "learning_rate": 5.402509924711612e-06, |
| "loss": 0.1248, |
| "mean_token_accuracy": 0.9567375779151917, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.6790697674418604, |
| "grad_norm": 2.249401569366455, |
| "learning_rate": 5.378142768957396e-06, |
| "loss": 0.165, |
| "mean_token_accuracy": 0.9445608258247375, |
| "step": 361 |
| }, |
| { |
| "epoch": 1.6837209302325582, |
| "grad_norm": 2.1428322792053223, |
| "learning_rate": 5.353779188350989e-06, |
| "loss": 0.1536, |
| "mean_token_accuracy": 0.9398339986801147, |
| "step": 362 |
| }, |
| { |
| "epoch": 1.688372093023256, |
| "grad_norm": 1.8637951612472534, |
| "learning_rate": 5.329419897691187e-06, |
| "loss": 0.1284, |
| "mean_token_accuracy": 0.9572995901107788, |
| "step": 363 |
| }, |
| { |
| "epoch": 1.6930232558139535, |
| "grad_norm": 2.081277847290039, |
| "learning_rate": 5.305065611650921e-06, |
| "loss": 0.1269, |
| "mean_token_accuracy": 0.9535707831382751, |
| "step": 364 |
| }, |
| { |
| "epoch": 1.697674418604651, |
| "grad_norm": 1.8109171390533447, |
| "learning_rate": 5.280717044756298e-06, |
| "loss": 0.1332, |
| "mean_token_accuracy": 0.9521582722663879, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.7023255813953488, |
| "grad_norm": 1.8539905548095703, |
| "learning_rate": 5.256374911365621e-06, |
| "loss": 0.141, |
| "mean_token_accuracy": 0.948835015296936, |
| "step": 366 |
| }, |
| { |
| "epoch": 1.7069767441860466, |
| "grad_norm": 1.6707813739776611, |
| "learning_rate": 5.232039925648457e-06, |
| "loss": 0.1112, |
| "mean_token_accuracy": 0.9606493711471558, |
| "step": 367 |
| }, |
| { |
| "epoch": 1.7116279069767442, |
| "grad_norm": 1.7835884094238281, |
| "learning_rate": 5.207712801564652e-06, |
| "loss": 0.1217, |
| "mean_token_accuracy": 0.9547820687294006, |
| "step": 368 |
| }, |
| { |
| "epoch": 1.7162790697674417, |
| "grad_norm": 1.926405668258667, |
| "learning_rate": 5.1833942528434145e-06, |
| "loss": 0.1283, |
| "mean_token_accuracy": 0.954860508441925, |
| "step": 369 |
| }, |
| { |
| "epoch": 1.7209302325581395, |
| "grad_norm": 1.9628880023956299, |
| "learning_rate": 5.159084992962354e-06, |
| "loss": 0.1176, |
| "mean_token_accuracy": 0.9579154849052429, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.7255813953488373, |
| "grad_norm": 1.838537335395813, |
| "learning_rate": 5.13478573512656e-06, |
| "loss": 0.1516, |
| "mean_token_accuracy": 0.9484519958496094, |
| "step": 371 |
| }, |
| { |
| "epoch": 1.730232558139535, |
| "grad_norm": 1.7399450540542603, |
| "learning_rate": 5.110497192247671e-06, |
| "loss": 0.1274, |
| "mean_token_accuracy": 0.9532235264778137, |
| "step": 372 |
| }, |
| { |
| "epoch": 1.7348837209302326, |
| "grad_norm": 1.798194169998169, |
| "learning_rate": 5.086220076922965e-06, |
| "loss": 0.1225, |
| "mean_token_accuracy": 0.9570792317390442, |
| "step": 373 |
| }, |
| { |
| "epoch": 1.7395348837209301, |
| "grad_norm": 2.0451667308807373, |
| "learning_rate": 5.061955101414448e-06, |
| "loss": 0.1517, |
| "mean_token_accuracy": 0.9501442909240723, |
| "step": 374 |
| }, |
| { |
| "epoch": 1.744186046511628, |
| "grad_norm": 1.874577522277832, |
| "learning_rate": 5.0377029776279514e-06, |
| "loss": 0.1227, |
| "mean_token_accuracy": 0.9561297297477722, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.7488372093023257, |
| "grad_norm": 1.733536958694458, |
| "learning_rate": 5.013464417092263e-06, |
| "loss": 0.1146, |
| "mean_token_accuracy": 0.9611798524856567, |
| "step": 376 |
| }, |
| { |
| "epoch": 1.7534883720930232, |
| "grad_norm": 1.8131812810897827, |
| "learning_rate": 4.989240130938232e-06, |
| "loss": 0.1218, |
| "mean_token_accuracy": 0.9619940519332886, |
| "step": 377 |
| }, |
| { |
| "epoch": 1.7581395348837208, |
| "grad_norm": 1.9327350854873657, |
| "learning_rate": 4.9650308298779215e-06, |
| "loss": 0.1452, |
| "mean_token_accuracy": 0.9495870471000671, |
| "step": 378 |
| }, |
| { |
| "epoch": 1.7627906976744185, |
| "grad_norm": 1.914912223815918, |
| "learning_rate": 4.940837224183742e-06, |
| "loss": 0.1221, |
| "mean_token_accuracy": 0.956214189529419, |
| "step": 379 |
| }, |
| { |
| "epoch": 1.7674418604651163, |
| "grad_norm": 1.8603955507278442, |
| "learning_rate": 4.916660023667627e-06, |
| "loss": 0.1394, |
| "mean_token_accuracy": 0.9508364796638489, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.772093023255814, |
| "grad_norm": 2.003020763397217, |
| "learning_rate": 4.892499937660195e-06, |
| "loss": 0.1318, |
| "mean_token_accuracy": 0.951373815536499, |
| "step": 381 |
| }, |
| { |
| "epoch": 1.7767441860465116, |
| "grad_norm": 2.2919867038726807, |
| "learning_rate": 4.8683576749899505e-06, |
| "loss": 0.1521, |
| "mean_token_accuracy": 0.9484791159629822, |
| "step": 382 |
| }, |
| { |
| "epoch": 1.7813953488372092, |
| "grad_norm": 1.9706724882125854, |
| "learning_rate": 4.844233943962481e-06, |
| "loss": 0.1103, |
| "mean_token_accuracy": 0.9585579037666321, |
| "step": 383 |
| }, |
| { |
| "epoch": 1.786046511627907, |
| "grad_norm": 1.9017114639282227, |
| "learning_rate": 4.820129452339676e-06, |
| "loss": 0.1439, |
| "mean_token_accuracy": 0.9472662806510925, |
| "step": 384 |
| }, |
| { |
| "epoch": 1.7906976744186047, |
| "grad_norm": 1.9794905185699463, |
| "learning_rate": 4.796044907318961e-06, |
| "loss": 0.137, |
| "mean_token_accuracy": 0.9533417224884033, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.7953488372093023, |
| "grad_norm": 2.379739284515381, |
| "learning_rate": 4.771981015512559e-06, |
| "loss": 0.1763, |
| "mean_token_accuracy": 0.9416927695274353, |
| "step": 386 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 1.9658362865447998, |
| "learning_rate": 4.747938482926746e-06, |
| "loss": 0.1481, |
| "mean_token_accuracy": 0.9476566314697266, |
| "step": 387 |
| }, |
| { |
| "epoch": 1.8046511627906976, |
| "grad_norm": 1.9675973653793335, |
| "learning_rate": 4.723918014941144e-06, |
| "loss": 0.1353, |
| "mean_token_accuracy": 0.9520778656005859, |
| "step": 388 |
| }, |
| { |
| "epoch": 1.8093023255813954, |
| "grad_norm": 1.9576362371444702, |
| "learning_rate": 4.69992031628803e-06, |
| "loss": 0.1286, |
| "mean_token_accuracy": 0.9561353921890259, |
| "step": 389 |
| }, |
| { |
| "epoch": 1.8139534883720931, |
| "grad_norm": 1.9920960664749146, |
| "learning_rate": 4.675946091031648e-06, |
| "loss": 0.1359, |
| "mean_token_accuracy": 0.9533660411834717, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.8186046511627907, |
| "grad_norm": 1.902557134628296, |
| "learning_rate": 4.65199604254757e-06, |
| "loss": 0.13, |
| "mean_token_accuracy": 0.9536868929862976, |
| "step": 391 |
| }, |
| { |
| "epoch": 1.8232558139534882, |
| "grad_norm": 1.7443137168884277, |
| "learning_rate": 4.628070873502038e-06, |
| "loss": 0.1346, |
| "mean_token_accuracy": 0.9529221057891846, |
| "step": 392 |
| }, |
| { |
| "epoch": 1.827906976744186, |
| "grad_norm": 1.5767067670822144, |
| "learning_rate": 4.604171285831373e-06, |
| "loss": 0.1128, |
| "mean_token_accuracy": 0.9544422626495361, |
| "step": 393 |
| }, |
| { |
| "epoch": 1.8325581395348838, |
| "grad_norm": 2.047105312347412, |
| "learning_rate": 4.5802979807213585e-06, |
| "loss": 0.1516, |
| "mean_token_accuracy": 0.9372674226760864, |
| "step": 394 |
| }, |
| { |
| "epoch": 1.8372093023255816, |
| "grad_norm": 1.8142563104629517, |
| "learning_rate": 4.556451658586687e-06, |
| "loss": 0.1226, |
| "mean_token_accuracy": 0.9564979076385498, |
| "step": 395 |
| }, |
| { |
| "epoch": 1.841860465116279, |
| "grad_norm": 1.9213443994522095, |
| "learning_rate": 4.532633019050392e-06, |
| "loss": 0.1438, |
| "mean_token_accuracy": 0.9534309506416321, |
| "step": 396 |
| }, |
| { |
| "epoch": 1.8465116279069766, |
| "grad_norm": 1.772811770439148, |
| "learning_rate": 4.508842760923344e-06, |
| "loss": 0.1358, |
| "mean_token_accuracy": 0.9528013467788696, |
| "step": 397 |
| }, |
| { |
| "epoch": 1.8511627906976744, |
| "grad_norm": 1.880860447883606, |
| "learning_rate": 4.4850815821837265e-06, |
| "loss": 0.1345, |
| "mean_token_accuracy": 0.9486945271492004, |
| "step": 398 |
| }, |
| { |
| "epoch": 1.8558139534883722, |
| "grad_norm": 2.0496411323547363, |
| "learning_rate": 4.4613501799565755e-06, |
| "loss": 0.1429, |
| "mean_token_accuracy": 0.9489778876304626, |
| "step": 399 |
| }, |
| { |
| "epoch": 1.8604651162790697, |
| "grad_norm": 1.9374741315841675, |
| "learning_rate": 4.43764925049331e-06, |
| "loss": 0.131, |
| "mean_token_accuracy": 0.9518900513648987, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.8651162790697673, |
| "grad_norm": 1.947840929031372, |
| "learning_rate": 4.413979489151326e-06, |
| "loss": 0.1399, |
| "mean_token_accuracy": 0.9489177465438843, |
| "step": 401 |
| }, |
| { |
| "epoch": 1.869767441860465, |
| "grad_norm": 2.468381643295288, |
| "learning_rate": 4.3903415903735725e-06, |
| "loss": 0.1656, |
| "mean_token_accuracy": 0.9420523643493652, |
| "step": 402 |
| }, |
| { |
| "epoch": 1.8744186046511628, |
| "grad_norm": 1.9637192487716675, |
| "learning_rate": 4.366736247668194e-06, |
| "loss": 0.1214, |
| "mean_token_accuracy": 0.9539300203323364, |
| "step": 403 |
| }, |
| { |
| "epoch": 1.8790697674418606, |
| "grad_norm": 1.993908405303955, |
| "learning_rate": 4.343164153588176e-06, |
| "loss": 0.1413, |
| "mean_token_accuracy": 0.95000821352005, |
| "step": 404 |
| }, |
| { |
| "epoch": 1.8837209302325582, |
| "grad_norm": 2.0856027603149414, |
| "learning_rate": 4.3196259997110326e-06, |
| "loss": 0.142, |
| "mean_token_accuracy": 0.949593186378479, |
| "step": 405 |
| }, |
| { |
| "epoch": 1.8883720930232557, |
| "grad_norm": 1.7070889472961426, |
| "learning_rate": 4.296122476618507e-06, |
| "loss": 0.1247, |
| "mean_token_accuracy": 0.9530761241912842, |
| "step": 406 |
| }, |
| { |
| "epoch": 1.8930232558139535, |
| "grad_norm": 1.9810974597930908, |
| "learning_rate": 4.2726542738763185e-06, |
| "loss": 0.1164, |
| "mean_token_accuracy": 0.9563318490982056, |
| "step": 407 |
| }, |
| { |
| "epoch": 1.8976744186046512, |
| "grad_norm": 2.0617589950561523, |
| "learning_rate": 4.249222080013927e-06, |
| "loss": 0.1543, |
| "mean_token_accuracy": 0.9469596743583679, |
| "step": 408 |
| }, |
| { |
| "epoch": 1.9023255813953488, |
| "grad_norm": 1.9862779378890991, |
| "learning_rate": 4.2258265825043365e-06, |
| "loss": 0.1297, |
| "mean_token_accuracy": 0.9529111385345459, |
| "step": 409 |
| }, |
| { |
| "epoch": 1.9069767441860463, |
| "grad_norm": 1.9495517015457153, |
| "learning_rate": 4.202468467743922e-06, |
| "loss": 0.1348, |
| "mean_token_accuracy": 0.9511424899101257, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.9116279069767441, |
| "grad_norm": 1.9612817764282227, |
| "learning_rate": 4.1791484210322945e-06, |
| "loss": 0.1424, |
| "mean_token_accuracy": 0.9513311982154846, |
| "step": 411 |
| }, |
| { |
| "epoch": 1.916279069767442, |
| "grad_norm": 1.9220209121704102, |
| "learning_rate": 4.15586712655219e-06, |
| "loss": 0.1338, |
| "mean_token_accuracy": 0.9528619647026062, |
| "step": 412 |
| }, |
| { |
| "epoch": 1.9209302325581397, |
| "grad_norm": 1.9853949546813965, |
| "learning_rate": 4.1326252673494006e-06, |
| "loss": 0.1367, |
| "mean_token_accuracy": 0.9542078971862793, |
| "step": 413 |
| }, |
| { |
| "epoch": 1.9255813953488372, |
| "grad_norm": 1.8623827695846558, |
| "learning_rate": 4.109423525312738e-06, |
| "loss": 0.1306, |
| "mean_token_accuracy": 0.9558945298194885, |
| "step": 414 |
| }, |
| { |
| "epoch": 1.9302325581395348, |
| "grad_norm": 2.083481550216675, |
| "learning_rate": 4.086262581154015e-06, |
| "loss": 0.1253, |
| "mean_token_accuracy": 0.9526870846748352, |
| "step": 415 |
| }, |
| { |
| "epoch": 1.9348837209302325, |
| "grad_norm": 1.816807508468628, |
| "learning_rate": 4.0631431143880915e-06, |
| "loss": 0.1352, |
| "mean_token_accuracy": 0.9498327970504761, |
| "step": 416 |
| }, |
| { |
| "epoch": 1.9395348837209303, |
| "grad_norm": 1.9113500118255615, |
| "learning_rate": 4.040065803312921e-06, |
| "loss": 0.1358, |
| "mean_token_accuracy": 0.948095440864563, |
| "step": 417 |
| }, |
| { |
| "epoch": 1.9441860465116279, |
| "grad_norm": 1.7576724290847778, |
| "learning_rate": 4.017031324989669e-06, |
| "loss": 0.1135, |
| "mean_token_accuracy": 0.9590513706207275, |
| "step": 418 |
| }, |
| { |
| "epoch": 1.9488372093023256, |
| "grad_norm": 2.2163145542144775, |
| "learning_rate": 3.994040355222828e-06, |
| "loss": 0.1438, |
| "mean_token_accuracy": 0.9499019384384155, |
| "step": 419 |
| }, |
| { |
| "epoch": 1.9534883720930232, |
| "grad_norm": 1.9273474216461182, |
| "learning_rate": 3.971093568540408e-06, |
| "loss": 0.1365, |
| "mean_token_accuracy": 0.9528368711471558, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.958139534883721, |
| "grad_norm": 1.855919361114502, |
| "learning_rate": 3.948191638174135e-06, |
| "loss": 0.1321, |
| "mean_token_accuracy": 0.9499024152755737, |
| "step": 421 |
| }, |
| { |
| "epoch": 1.9627906976744187, |
| "grad_norm": 2.040865659713745, |
| "learning_rate": 3.925335236039702e-06, |
| "loss": 0.1394, |
| "mean_token_accuracy": 0.9538987874984741, |
| "step": 422 |
| }, |
| { |
| "epoch": 1.9674418604651163, |
| "grad_norm": 1.827325701713562, |
| "learning_rate": 3.902525032717067e-06, |
| "loss": 0.1056, |
| "mean_token_accuracy": 0.9614977240562439, |
| "step": 423 |
| }, |
| { |
| "epoch": 1.9720930232558138, |
| "grad_norm": 1.778291940689087, |
| "learning_rate": 3.879761697430756e-06, |
| "loss": 0.1247, |
| "mean_token_accuracy": 0.9552616477012634, |
| "step": 424 |
| }, |
| { |
| "epoch": 1.9767441860465116, |
| "grad_norm": 1.7589936256408691, |
| "learning_rate": 3.8570458980302526e-06, |
| "loss": 0.1262, |
| "mean_token_accuracy": 0.9544051885604858, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.9813953488372094, |
| "grad_norm": 1.8840413093566895, |
| "learning_rate": 3.834378300970385e-06, |
| "loss": 0.1317, |
| "mean_token_accuracy": 0.9542329907417297, |
| "step": 426 |
| }, |
| { |
| "epoch": 1.9860465116279071, |
| "grad_norm": 2.0406875610351562, |
| "learning_rate": 3.811759571291792e-06, |
| "loss": 0.1298, |
| "mean_token_accuracy": 0.9538700580596924, |
| "step": 427 |
| }, |
| { |
| "epoch": 1.9906976744186047, |
| "grad_norm": 1.8465980291366577, |
| "learning_rate": 3.789190372601387e-06, |
| "loss": 0.1456, |
| "mean_token_accuracy": 0.9468926787376404, |
| "step": 428 |
| }, |
| { |
| "epoch": 1.9953488372093022, |
| "grad_norm": 1.9541380405426025, |
| "learning_rate": 3.7666713670529153e-06, |
| "loss": 0.1409, |
| "mean_token_accuracy": 0.9509699940681458, |
| "step": 429 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.4541330337524414, |
| "learning_rate": 3.7442032153275053e-06, |
| "loss": 0.0761, |
| "mean_token_accuracy": 0.9719982743263245, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.0046511627906978, |
| "grad_norm": 1.672062635421753, |
| "learning_rate": 3.7217865766143014e-06, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.984748363494873, |
| "step": 431 |
| }, |
| { |
| "epoch": 2.0093023255813955, |
| "grad_norm": 1.4939134120941162, |
| "learning_rate": 3.6994221085911107e-06, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.9857293963432312, |
| "step": 432 |
| }, |
| { |
| "epoch": 2.013953488372093, |
| "grad_norm": 1.3394852876663208, |
| "learning_rate": 3.6771104674051184e-06, |
| "loss": 0.0461, |
| "mean_token_accuracy": 0.9873949289321899, |
| "step": 433 |
| }, |
| { |
| "epoch": 2.0186046511627906, |
| "grad_norm": 1.4517439603805542, |
| "learning_rate": 3.654852307653628e-06, |
| "loss": 0.048, |
| "mean_token_accuracy": 0.9845333099365234, |
| "step": 434 |
| }, |
| { |
| "epoch": 2.0232558139534884, |
| "grad_norm": 1.157000184059143, |
| "learning_rate": 3.6326482823648656e-06, |
| "loss": 0.0412, |
| "mean_token_accuracy": 0.9895949363708496, |
| "step": 435 |
| }, |
| { |
| "epoch": 2.027906976744186, |
| "grad_norm": 1.5402953624725342, |
| "learning_rate": 3.6104990429788102e-06, |
| "loss": 0.0387, |
| "mean_token_accuracy": 0.9885908365249634, |
| "step": 436 |
| }, |
| { |
| "epoch": 2.0325581395348835, |
| "grad_norm": 1.3295921087265015, |
| "learning_rate": 3.588405239328091e-06, |
| "loss": 0.0485, |
| "mean_token_accuracy": 0.9842379093170166, |
| "step": 437 |
| }, |
| { |
| "epoch": 2.0372093023255813, |
| "grad_norm": 1.5409480333328247, |
| "learning_rate": 3.5663675196189184e-06, |
| "loss": 0.0452, |
| "mean_token_accuracy": 0.9862408638000488, |
| "step": 438 |
| }, |
| { |
| "epoch": 2.041860465116279, |
| "grad_norm": 1.2995237112045288, |
| "learning_rate": 3.5443865304120607e-06, |
| "loss": 0.0361, |
| "mean_token_accuracy": 0.9853552579879761, |
| "step": 439 |
| }, |
| { |
| "epoch": 2.046511627906977, |
| "grad_norm": 1.1838889122009277, |
| "learning_rate": 3.522462916603887e-06, |
| "loss": 0.0394, |
| "mean_token_accuracy": 0.9879562258720398, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.0511627906976746, |
| "grad_norm": 1.304025411605835, |
| "learning_rate": 3.500597321407435e-06, |
| "loss": 0.0313, |
| "mean_token_accuracy": 0.9885208010673523, |
| "step": 441 |
| }, |
| { |
| "epoch": 2.055813953488372, |
| "grad_norm": 1.6431220769882202, |
| "learning_rate": 3.478790386333546e-06, |
| "loss": 0.0471, |
| "mean_token_accuracy": 0.9840630292892456, |
| "step": 442 |
| }, |
| { |
| "epoch": 2.0604651162790697, |
| "grad_norm": 2.0246262550354004, |
| "learning_rate": 3.45704275117204e-06, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.9822935461997986, |
| "step": 443 |
| }, |
| { |
| "epoch": 2.0651162790697675, |
| "grad_norm": 1.8200246095657349, |
| "learning_rate": 3.435355053972953e-06, |
| "loss": 0.0488, |
| "mean_token_accuracy": 0.9845336079597473, |
| "step": 444 |
| }, |
| { |
| "epoch": 2.0697674418604652, |
| "grad_norm": 2.0698256492614746, |
| "learning_rate": 3.4137279310278054e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9742683172225952, |
| "step": 445 |
| }, |
| { |
| "epoch": 2.0744186046511626, |
| "grad_norm": 1.9601695537567139, |
| "learning_rate": 3.392162016850945e-06, |
| "loss": 0.054, |
| "mean_token_accuracy": 0.9828470945358276, |
| "step": 446 |
| }, |
| { |
| "epoch": 2.0790697674418603, |
| "grad_norm": 1.7648512125015259, |
| "learning_rate": 3.3706579441609224e-06, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9847809672355652, |
| "step": 447 |
| }, |
| { |
| "epoch": 2.083720930232558, |
| "grad_norm": 2.1309351921081543, |
| "learning_rate": 3.3492163438619362e-06, |
| "loss": 0.0499, |
| "mean_token_accuracy": 0.9843156933784485, |
| "step": 448 |
| }, |
| { |
| "epoch": 2.088372093023256, |
| "grad_norm": 1.4552912712097168, |
| "learning_rate": 3.327837845025315e-06, |
| "loss": 0.0471, |
| "mean_token_accuracy": 0.9860197305679321, |
| "step": 449 |
| }, |
| { |
| "epoch": 2.0930232558139537, |
| "grad_norm": 1.743163824081421, |
| "learning_rate": 3.3065230748710646e-06, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.984899640083313, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.097674418604651, |
| "grad_norm": 1.6881510019302368, |
| "learning_rate": 3.2852726587494673e-06, |
| "loss": 0.0457, |
| "mean_token_accuracy": 0.9868685007095337, |
| "step": 451 |
| }, |
| { |
| "epoch": 2.1023255813953488, |
| "grad_norm": 1.7363135814666748, |
| "learning_rate": 3.2640872201227364e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9822916388511658, |
| "step": 452 |
| }, |
| { |
| "epoch": 2.1069767441860465, |
| "grad_norm": 1.500846266746521, |
| "learning_rate": 3.242967380546717e-06, |
| "loss": 0.047, |
| "mean_token_accuracy": 0.9842950105667114, |
| "step": 453 |
| }, |
| { |
| "epoch": 2.1116279069767443, |
| "grad_norm": 1.7576566934585571, |
| "learning_rate": 3.221913759652657e-06, |
| "loss": 0.0488, |
| "mean_token_accuracy": 0.9847888350486755, |
| "step": 454 |
| }, |
| { |
| "epoch": 2.116279069767442, |
| "grad_norm": 1.6291195154190063, |
| "learning_rate": 3.20092697512903e-06, |
| "loss": 0.0483, |
| "mean_token_accuracy": 0.9865509271621704, |
| "step": 455 |
| }, |
| { |
| "epoch": 2.1209302325581394, |
| "grad_norm": 1.565114974975586, |
| "learning_rate": 3.180007642703402e-06, |
| "loss": 0.0439, |
| "mean_token_accuracy": 0.9828610420227051, |
| "step": 456 |
| }, |
| { |
| "epoch": 2.125581395348837, |
| "grad_norm": 1.3543715476989746, |
| "learning_rate": 3.1591563761243816e-06, |
| "loss": 0.0406, |
| "mean_token_accuracy": 0.9870887994766235, |
| "step": 457 |
| }, |
| { |
| "epoch": 2.130232558139535, |
| "grad_norm": 1.4812368154525757, |
| "learning_rate": 3.138373787143598e-06, |
| "loss": 0.0424, |
| "mean_token_accuracy": 0.9881157279014587, |
| "step": 458 |
| }, |
| { |
| "epoch": 2.1348837209302327, |
| "grad_norm": 1.2913554906845093, |
| "learning_rate": 3.1176604854977665e-06, |
| "loss": 0.0393, |
| "mean_token_accuracy": 0.988473653793335, |
| "step": 459 |
| }, |
| { |
| "epoch": 2.13953488372093, |
| "grad_norm": 1.317392349243164, |
| "learning_rate": 3.0970170788907878e-06, |
| "loss": 0.0388, |
| "mean_token_accuracy": 0.9886342883110046, |
| "step": 460 |
| }, |
| { |
| "epoch": 2.144186046511628, |
| "grad_norm": 1.1565263271331787, |
| "learning_rate": 3.076444172975932e-06, |
| "loss": 0.0383, |
| "mean_token_accuracy": 0.9860601425170898, |
| "step": 461 |
| }, |
| { |
| "epoch": 2.1488372093023256, |
| "grad_norm": 1.3981534242630005, |
| "learning_rate": 3.055942371338052e-06, |
| "loss": 0.0473, |
| "mean_token_accuracy": 0.9850096106529236, |
| "step": 462 |
| }, |
| { |
| "epoch": 2.1534883720930234, |
| "grad_norm": 1.1593438386917114, |
| "learning_rate": 3.035512275475896e-06, |
| "loss": 0.038, |
| "mean_token_accuracy": 0.987267017364502, |
| "step": 463 |
| }, |
| { |
| "epoch": 2.158139534883721, |
| "grad_norm": 1.4584743976593018, |
| "learning_rate": 3.0151544847844385e-06, |
| "loss": 0.0457, |
| "mean_token_accuracy": 0.9883371591567993, |
| "step": 464 |
| }, |
| { |
| "epoch": 2.1627906976744184, |
| "grad_norm": 1.349255084991455, |
| "learning_rate": 2.994869596537316e-06, |
| "loss": 0.0386, |
| "mean_token_accuracy": 0.9858284592628479, |
| "step": 465 |
| }, |
| { |
| "epoch": 2.167441860465116, |
| "grad_norm": 1.4808646440505981, |
| "learning_rate": 2.9746582058692803e-06, |
| "loss": 0.0419, |
| "mean_token_accuracy": 0.9876099228858948, |
| "step": 466 |
| }, |
| { |
| "epoch": 2.172093023255814, |
| "grad_norm": 1.5003681182861328, |
| "learning_rate": 2.954520905758762e-06, |
| "loss": 0.0437, |
| "mean_token_accuracy": 0.9860689640045166, |
| "step": 467 |
| }, |
| { |
| "epoch": 2.1767441860465118, |
| "grad_norm": 1.2506943941116333, |
| "learning_rate": 2.934458287010455e-06, |
| "loss": 0.0327, |
| "mean_token_accuracy": 0.9890545606613159, |
| "step": 468 |
| }, |
| { |
| "epoch": 2.181395348837209, |
| "grad_norm": 1.4070329666137695, |
| "learning_rate": 2.9144709382379955e-06, |
| "loss": 0.0429, |
| "mean_token_accuracy": 0.9838380813598633, |
| "step": 469 |
| }, |
| { |
| "epoch": 2.186046511627907, |
| "grad_norm": 1.844129204750061, |
| "learning_rate": 2.894559445846682e-06, |
| "loss": 0.0488, |
| "mean_token_accuracy": 0.9844542741775513, |
| "step": 470 |
| }, |
| { |
| "epoch": 2.1906976744186046, |
| "grad_norm": 1.729974389076233, |
| "learning_rate": 2.8747243940162774e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9824362397193909, |
| "step": 471 |
| }, |
| { |
| "epoch": 2.1953488372093024, |
| "grad_norm": 1.6033308506011963, |
| "learning_rate": 2.854966364683872e-06, |
| "loss": 0.0338, |
| "mean_token_accuracy": 0.9885597825050354, |
| "step": 472 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 1.332747459411621, |
| "learning_rate": 2.835285937526801e-06, |
| "loss": 0.044, |
| "mean_token_accuracy": 0.9859412908554077, |
| "step": 473 |
| }, |
| { |
| "epoch": 2.2046511627906975, |
| "grad_norm": 1.7800264358520508, |
| "learning_rate": 2.8156836899456475e-06, |
| "loss": 0.0487, |
| "mean_token_accuracy": 0.9829608201980591, |
| "step": 474 |
| }, |
| { |
| "epoch": 2.2093023255813953, |
| "grad_norm": 1.664980173110962, |
| "learning_rate": 2.796160197047294e-06, |
| "loss": 0.0464, |
| "mean_token_accuracy": 0.9837183952331543, |
| "step": 475 |
| }, |
| { |
| "epoch": 2.213953488372093, |
| "grad_norm": 1.2077975273132324, |
| "learning_rate": 2.7767160316280583e-06, |
| "loss": 0.0303, |
| "mean_token_accuracy": 0.9894075989723206, |
| "step": 476 |
| }, |
| { |
| "epoch": 2.218604651162791, |
| "grad_norm": 1.418182373046875, |
| "learning_rate": 2.757351764156877e-06, |
| "loss": 0.0395, |
| "mean_token_accuracy": 0.9862279891967773, |
| "step": 477 |
| }, |
| { |
| "epoch": 2.2232558139534886, |
| "grad_norm": 1.4983257055282593, |
| "learning_rate": 2.7380679627585817e-06, |
| "loss": 0.0444, |
| "mean_token_accuracy": 0.9853575825691223, |
| "step": 478 |
| }, |
| { |
| "epoch": 2.227906976744186, |
| "grad_norm": 1.423553466796875, |
| "learning_rate": 2.718865193197218e-06, |
| "loss": 0.0409, |
| "mean_token_accuracy": 0.9856008887290955, |
| "step": 479 |
| }, |
| { |
| "epoch": 2.2325581395348837, |
| "grad_norm": 1.4247428178787231, |
| "learning_rate": 2.699744018859457e-06, |
| "loss": 0.0462, |
| "mean_token_accuracy": 0.9839481115341187, |
| "step": 480 |
| }, |
| { |
| "epoch": 2.2372093023255815, |
| "grad_norm": 1.2295563220977783, |
| "learning_rate": 2.680705000738061e-06, |
| "loss": 0.0368, |
| "mean_token_accuracy": 0.9896710515022278, |
| "step": 481 |
| }, |
| { |
| "epoch": 2.2418604651162792, |
| "grad_norm": 1.374080777168274, |
| "learning_rate": 2.661748697415423e-06, |
| "loss": 0.0409, |
| "mean_token_accuracy": 0.9884670972824097, |
| "step": 482 |
| }, |
| { |
| "epoch": 2.2465116279069766, |
| "grad_norm": 1.4290623664855957, |
| "learning_rate": 2.642875665047182e-06, |
| "loss": 0.049, |
| "mean_token_accuracy": 0.9858566522598267, |
| "step": 483 |
| }, |
| { |
| "epoch": 2.2511627906976743, |
| "grad_norm": 1.8040648698806763, |
| "learning_rate": 2.6240864573459095e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9802747368812561, |
| "step": 484 |
| }, |
| { |
| "epoch": 2.255813953488372, |
| "grad_norm": 1.3592660427093506, |
| "learning_rate": 2.6053816255648543e-06, |
| "loss": 0.0326, |
| "mean_token_accuracy": 0.9880083203315735, |
| "step": 485 |
| }, |
| { |
| "epoch": 2.26046511627907, |
| "grad_norm": 1.4660333395004272, |
| "learning_rate": 2.586761718481776e-06, |
| "loss": 0.0431, |
| "mean_token_accuracy": 0.9855907559394836, |
| "step": 486 |
| }, |
| { |
| "epoch": 2.265116279069767, |
| "grad_norm": 1.5499329566955566, |
| "learning_rate": 2.5682272823828474e-06, |
| "loss": 0.0447, |
| "mean_token_accuracy": 0.9844789505004883, |
| "step": 487 |
| }, |
| { |
| "epoch": 2.269767441860465, |
| "grad_norm": 1.3596184253692627, |
| "learning_rate": 2.5497788610466177e-06, |
| "loss": 0.0372, |
| "mean_token_accuracy": 0.9874828457832336, |
| "step": 488 |
| }, |
| { |
| "epoch": 2.2744186046511627, |
| "grad_norm": 1.2610822916030884, |
| "learning_rate": 2.53141699572807e-06, |
| "loss": 0.038, |
| "mean_token_accuracy": 0.9895055294036865, |
| "step": 489 |
| }, |
| { |
| "epoch": 2.2790697674418605, |
| "grad_norm": 1.4940454959869385, |
| "learning_rate": 2.5131422251427313e-06, |
| "loss": 0.043, |
| "mean_token_accuracy": 0.986737847328186, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.2837209302325583, |
| "grad_norm": 1.3737494945526123, |
| "learning_rate": 2.4949550854508713e-06, |
| "loss": 0.0368, |
| "mean_token_accuracy": 0.9881452918052673, |
| "step": 491 |
| }, |
| { |
| "epoch": 2.2883720930232556, |
| "grad_norm": 1.7707860469818115, |
| "learning_rate": 2.476856110241773e-06, |
| "loss": 0.0394, |
| "mean_token_accuracy": 0.9883301854133606, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.2930232558139534, |
| "grad_norm": 1.5083131790161133, |
| "learning_rate": 2.458845830518082e-06, |
| "loss": 0.0469, |
| "mean_token_accuracy": 0.9832764863967896, |
| "step": 493 |
| }, |
| { |
| "epoch": 2.297674418604651, |
| "grad_norm": 1.5373071432113647, |
| "learning_rate": 2.440924774680215e-06, |
| "loss": 0.0469, |
| "mean_token_accuracy": 0.9855247139930725, |
| "step": 494 |
| }, |
| { |
| "epoch": 2.302325581395349, |
| "grad_norm": 1.5899007320404053, |
| "learning_rate": 2.4230934685108707e-06, |
| "loss": 0.0445, |
| "mean_token_accuracy": 0.9864286780357361, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.3069767441860467, |
| "grad_norm": 1.281482219696045, |
| "learning_rate": 2.405352435159595e-06, |
| "loss": 0.0404, |
| "mean_token_accuracy": 0.985908567905426, |
| "step": 496 |
| }, |
| { |
| "epoch": 2.311627906976744, |
| "grad_norm": 1.8610132932662964, |
| "learning_rate": 2.3877021951274374e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9820767641067505, |
| "step": 497 |
| }, |
| { |
| "epoch": 2.316279069767442, |
| "grad_norm": 1.4103353023529053, |
| "learning_rate": 2.3701432662516772e-06, |
| "loss": 0.0396, |
| "mean_token_accuracy": 0.9848379492759705, |
| "step": 498 |
| }, |
| { |
| "epoch": 2.3209302325581396, |
| "grad_norm": 1.7032541036605835, |
| "learning_rate": 2.3526761636906313e-06, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9844515919685364, |
| "step": 499 |
| }, |
| { |
| "epoch": 2.3255813953488373, |
| "grad_norm": 1.4253147840499878, |
| "learning_rate": 2.3353013999085402e-06, |
| "loss": 0.0452, |
| "mean_token_accuracy": 0.9855325818061829, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.330232558139535, |
| "grad_norm": 1.3063850402832031, |
| "learning_rate": 2.3180194846605367e-06, |
| "loss": 0.0353, |
| "mean_token_accuracy": 0.9888969659805298, |
| "step": 501 |
| }, |
| { |
| "epoch": 2.3348837209302324, |
| "grad_norm": 1.183137059211731, |
| "learning_rate": 2.300830924977683e-06, |
| "loss": 0.03, |
| "mean_token_accuracy": 0.9909448623657227, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.33953488372093, |
| "grad_norm": 1.4097849130630493, |
| "learning_rate": 2.283736225152099e-06, |
| "loss": 0.0404, |
| "mean_token_accuracy": 0.9841188788414001, |
| "step": 503 |
| }, |
| { |
| "epoch": 2.344186046511628, |
| "grad_norm": 1.1793756484985352, |
| "learning_rate": 2.26673588672217e-06, |
| "loss": 0.0299, |
| "mean_token_accuracy": 0.9909354448318481, |
| "step": 504 |
| }, |
| { |
| "epoch": 2.3488372093023258, |
| "grad_norm": 1.328304648399353, |
| "learning_rate": 2.249830408457826e-06, |
| "loss": 0.0384, |
| "mean_token_accuracy": 0.9873096346855164, |
| "step": 505 |
| }, |
| { |
| "epoch": 2.353488372093023, |
| "grad_norm": 1.3120323419570923, |
| "learning_rate": 2.2330202863459123e-06, |
| "loss": 0.0375, |
| "mean_token_accuracy": 0.9867841601371765, |
| "step": 506 |
| }, |
| { |
| "epoch": 2.358139534883721, |
| "grad_norm": 1.3818902969360352, |
| "learning_rate": 2.2163060135756364e-06, |
| "loss": 0.0459, |
| "mean_token_accuracy": 0.985027551651001, |
| "step": 507 |
| }, |
| { |
| "epoch": 2.3627906976744186, |
| "grad_norm": 1.4502382278442383, |
| "learning_rate": 2.1996880805241e-06, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.9835244417190552, |
| "step": 508 |
| }, |
| { |
| "epoch": 2.3674418604651164, |
| "grad_norm": 1.435464859008789, |
| "learning_rate": 2.1831669747419093e-06, |
| "loss": 0.0442, |
| "mean_token_accuracy": 0.9855555295944214, |
| "step": 509 |
| }, |
| { |
| "epoch": 2.3720930232558137, |
| "grad_norm": 1.2933567762374878, |
| "learning_rate": 2.166743180938875e-06, |
| "loss": 0.0392, |
| "mean_token_accuracy": 0.9858629703521729, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.3767441860465115, |
| "grad_norm": 1.3595428466796875, |
| "learning_rate": 2.150417180969784e-06, |
| "loss": 0.0466, |
| "mean_token_accuracy": 0.9843334555625916, |
| "step": 511 |
| }, |
| { |
| "epoch": 2.3813953488372093, |
| "grad_norm": 1.5175772905349731, |
| "learning_rate": 2.1341894538202726e-06, |
| "loss": 0.0469, |
| "mean_token_accuracy": 0.9825721979141235, |
| "step": 512 |
| }, |
| { |
| "epoch": 2.386046511627907, |
| "grad_norm": 1.3737074136734009, |
| "learning_rate": 2.1180604755927646e-06, |
| "loss": 0.0452, |
| "mean_token_accuracy": 0.9853906631469727, |
| "step": 513 |
| }, |
| { |
| "epoch": 2.390697674418605, |
| "grad_norm": 1.5613442659378052, |
| "learning_rate": 2.102030719492508e-06, |
| "loss": 0.0404, |
| "mean_token_accuracy": 0.9870796799659729, |
| "step": 514 |
| }, |
| { |
| "epoch": 2.395348837209302, |
| "grad_norm": 1.5499093532562256, |
| "learning_rate": 2.086100655813688e-06, |
| "loss": 0.0497, |
| "mean_token_accuracy": 0.9838182330131531, |
| "step": 515 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 1.4529976844787598, |
| "learning_rate": 2.0702707519256365e-06, |
| "loss": 0.038, |
| "mean_token_accuracy": 0.9871166944503784, |
| "step": 516 |
| }, |
| { |
| "epoch": 2.4046511627906977, |
| "grad_norm": 1.3648254871368408, |
| "learning_rate": 2.0545414722591096e-06, |
| "loss": 0.0282, |
| "mean_token_accuracy": 0.9895697236061096, |
| "step": 517 |
| }, |
| { |
| "epoch": 2.4093023255813955, |
| "grad_norm": 1.286002278327942, |
| "learning_rate": 2.03891327829267e-06, |
| "loss": 0.0362, |
| "mean_token_accuracy": 0.9883317351341248, |
| "step": 518 |
| }, |
| { |
| "epoch": 2.4139534883720932, |
| "grad_norm": 1.480312705039978, |
| "learning_rate": 2.0233866285391455e-06, |
| "loss": 0.0402, |
| "mean_token_accuracy": 0.9887310266494751, |
| "step": 519 |
| }, |
| { |
| "epoch": 2.4186046511627906, |
| "grad_norm": 1.3333568572998047, |
| "learning_rate": 2.0079619785321713e-06, |
| "loss": 0.0376, |
| "mean_token_accuracy": 0.9858761429786682, |
| "step": 520 |
| }, |
| { |
| "epoch": 2.4232558139534883, |
| "grad_norm": 1.8251371383666992, |
| "learning_rate": 1.992639780812838e-06, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9830413460731506, |
| "step": 521 |
| }, |
| { |
| "epoch": 2.427906976744186, |
| "grad_norm": 1.3543392419815063, |
| "learning_rate": 1.9774204849164004e-06, |
| "loss": 0.0388, |
| "mean_token_accuracy": 0.9868179559707642, |
| "step": 522 |
| }, |
| { |
| "epoch": 2.432558139534884, |
| "grad_norm": 1.6293071508407593, |
| "learning_rate": 1.9623045373590955e-06, |
| "loss": 0.0474, |
| "mean_token_accuracy": 0.98483806848526, |
| "step": 523 |
| }, |
| { |
| "epoch": 2.4372093023255816, |
| "grad_norm": 1.60429048538208, |
| "learning_rate": 1.9472923816250427e-06, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.9808722138404846, |
| "step": 524 |
| }, |
| { |
| "epoch": 2.441860465116279, |
| "grad_norm": 1.6416536569595337, |
| "learning_rate": 1.9323844581532334e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.982349157333374, |
| "step": 525 |
| }, |
| { |
| "epoch": 2.4465116279069767, |
| "grad_norm": 1.429345965385437, |
| "learning_rate": 1.9175812043246034e-06, |
| "loss": 0.0446, |
| "mean_token_accuracy": 0.9842494130134583, |
| "step": 526 |
| }, |
| { |
| "epoch": 2.4511627906976745, |
| "grad_norm": 1.3102144002914429, |
| "learning_rate": 1.9028830544492074e-06, |
| "loss": 0.0468, |
| "mean_token_accuracy": 0.986748218536377, |
| "step": 527 |
| }, |
| { |
| "epoch": 2.4558139534883723, |
| "grad_norm": 1.4732224941253662, |
| "learning_rate": 1.8882904397534705e-06, |
| "loss": 0.0498, |
| "mean_token_accuracy": 0.9829692840576172, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.4604651162790696, |
| "grad_norm": 1.5619550943374634, |
| "learning_rate": 1.8738037883675445e-06, |
| "loss": 0.0437, |
| "mean_token_accuracy": 0.985709011554718, |
| "step": 529 |
| }, |
| { |
| "epoch": 2.4651162790697674, |
| "grad_norm": 1.7753974199295044, |
| "learning_rate": 1.8594235253127373e-06, |
| "loss": 0.0456, |
| "mean_token_accuracy": 0.9833365678787231, |
| "step": 530 |
| }, |
| { |
| "epoch": 2.469767441860465, |
| "grad_norm": 2.730788230895996, |
| "learning_rate": 1.8451500724890509e-06, |
| "loss": 0.0539, |
| "mean_token_accuracy": 0.9825479984283447, |
| "step": 531 |
| }, |
| { |
| "epoch": 2.474418604651163, |
| "grad_norm": 1.3585683107376099, |
| "learning_rate": 1.8309838486627995e-06, |
| "loss": 0.0382, |
| "mean_token_accuracy": 0.9866841435432434, |
| "step": 532 |
| }, |
| { |
| "epoch": 2.4790697674418603, |
| "grad_norm": 1.2621618509292603, |
| "learning_rate": 1.816925269454327e-06, |
| "loss": 0.036, |
| "mean_token_accuracy": 0.9900875687599182, |
| "step": 533 |
| }, |
| { |
| "epoch": 2.483720930232558, |
| "grad_norm": 1.179105281829834, |
| "learning_rate": 1.8029747473258092e-06, |
| "loss": 0.0375, |
| "mean_token_accuracy": 0.9860317707061768, |
| "step": 534 |
| }, |
| { |
| "epoch": 2.488372093023256, |
| "grad_norm": 1.4229761362075806, |
| "learning_rate": 1.789132691569153e-06, |
| "loss": 0.044, |
| "mean_token_accuracy": 0.9868127703666687, |
| "step": 535 |
| }, |
| { |
| "epoch": 2.4930232558139536, |
| "grad_norm": 1.4325740337371826, |
| "learning_rate": 1.7753995082939932e-06, |
| "loss": 0.0396, |
| "mean_token_accuracy": 0.9883702397346497, |
| "step": 536 |
| }, |
| { |
| "epoch": 2.4976744186046513, |
| "grad_norm": 1.7136763334274292, |
| "learning_rate": 1.7617756004157693e-06, |
| "loss": 0.0449, |
| "mean_token_accuracy": 0.9851675629615784, |
| "step": 537 |
| }, |
| { |
| "epoch": 2.5023255813953487, |
| "grad_norm": 1.3397361040115356, |
| "learning_rate": 1.7482613676439153e-06, |
| "loss": 0.0332, |
| "mean_token_accuracy": 0.9883018136024475, |
| "step": 538 |
| }, |
| { |
| "epoch": 2.5069767441860464, |
| "grad_norm": 1.3754647970199585, |
| "learning_rate": 1.7348572064701188e-06, |
| "loss": 0.0408, |
| "mean_token_accuracy": 0.9865552186965942, |
| "step": 539 |
| }, |
| { |
| "epoch": 2.511627906976744, |
| "grad_norm": 1.7942336797714233, |
| "learning_rate": 1.721563510156704e-06, |
| "loss": 0.0473, |
| "mean_token_accuracy": 0.9843230247497559, |
| "step": 540 |
| }, |
| { |
| "epoch": 2.516279069767442, |
| "grad_norm": 1.3669971227645874, |
| "learning_rate": 1.7083806687250795e-06, |
| "loss": 0.0397, |
| "mean_token_accuracy": 0.9862712621688843, |
| "step": 541 |
| }, |
| { |
| "epoch": 2.5209302325581397, |
| "grad_norm": 1.8536146879196167, |
| "learning_rate": 1.6953090689443074e-06, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.9839886426925659, |
| "step": 542 |
| }, |
| { |
| "epoch": 2.525581395348837, |
| "grad_norm": 1.4202018976211548, |
| "learning_rate": 1.6823490943197473e-06, |
| "loss": 0.043, |
| "mean_token_accuracy": 0.9865095615386963, |
| "step": 543 |
| }, |
| { |
| "epoch": 2.530232558139535, |
| "grad_norm": 1.3330633640289307, |
| "learning_rate": 1.6695011250818094e-06, |
| "loss": 0.0366, |
| "mean_token_accuracy": 0.9892926812171936, |
| "step": 544 |
| }, |
| { |
| "epoch": 2.5348837209302326, |
| "grad_norm": 1.459529995918274, |
| "learning_rate": 1.6567655381747976e-06, |
| "loss": 0.0358, |
| "mean_token_accuracy": 0.9880861043930054, |
| "step": 545 |
| }, |
| { |
| "epoch": 2.5395348837209304, |
| "grad_norm": 1.371484637260437, |
| "learning_rate": 1.6441427072458493e-06, |
| "loss": 0.0362, |
| "mean_token_accuracy": 0.986931324005127, |
| "step": 546 |
| }, |
| { |
| "epoch": 2.544186046511628, |
| "grad_norm": 1.6280467510223389, |
| "learning_rate": 1.6316330026339743e-06, |
| "loss": 0.0513, |
| "mean_token_accuracy": 0.9837538599967957, |
| "step": 547 |
| }, |
| { |
| "epoch": 2.5488372093023255, |
| "grad_norm": 1.2390743494033813, |
| "learning_rate": 1.6192367913591916e-06, |
| "loss": 0.043, |
| "mean_token_accuracy": 0.9854939579963684, |
| "step": 548 |
| }, |
| { |
| "epoch": 2.5534883720930233, |
| "grad_norm": 1.5508155822753906, |
| "learning_rate": 1.6069544371117556e-06, |
| "loss": 0.0441, |
| "mean_token_accuracy": 0.9845935702323914, |
| "step": 549 |
| }, |
| { |
| "epoch": 2.558139534883721, |
| "grad_norm": 1.206674575805664, |
| "learning_rate": 1.5947863002414938e-06, |
| "loss": 0.0374, |
| "mean_token_accuracy": 0.9881819486618042, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.5627906976744184, |
| "grad_norm": 1.4385532140731812, |
| "learning_rate": 1.5827327377472262e-06, |
| "loss": 0.0393, |
| "mean_token_accuracy": 0.9884690642356873, |
| "step": 551 |
| }, |
| { |
| "epoch": 2.567441860465116, |
| "grad_norm": 1.3227328062057495, |
| "learning_rate": 1.5707941032662967e-06, |
| "loss": 0.0433, |
| "mean_token_accuracy": 0.9855563640594482, |
| "step": 552 |
| }, |
| { |
| "epoch": 2.572093023255814, |
| "grad_norm": 1.3581526279449463, |
| "learning_rate": 1.558970747064198e-06, |
| "loss": 0.0414, |
| "mean_token_accuracy": 0.9869475960731506, |
| "step": 553 |
| }, |
| { |
| "epoch": 2.5767441860465117, |
| "grad_norm": 1.4792921543121338, |
| "learning_rate": 1.5472630160242921e-06, |
| "loss": 0.0434, |
| "mean_token_accuracy": 0.9850654602050781, |
| "step": 554 |
| }, |
| { |
| "epoch": 2.5813953488372094, |
| "grad_norm": 1.4469318389892578, |
| "learning_rate": 1.5356712536376345e-06, |
| "loss": 0.0451, |
| "mean_token_accuracy": 0.9870730638504028, |
| "step": 555 |
| }, |
| { |
| "epoch": 2.5860465116279068, |
| "grad_norm": 1.2094733715057373, |
| "learning_rate": 1.5241957999928974e-06, |
| "loss": 0.0324, |
| "mean_token_accuracy": 0.9892438054084778, |
| "step": 556 |
| }, |
| { |
| "epoch": 2.5906976744186045, |
| "grad_norm": 1.3837049007415771, |
| "learning_rate": 1.5128369917663924e-06, |
| "loss": 0.0358, |
| "mean_token_accuracy": 0.9864327311515808, |
| "step": 557 |
| }, |
| { |
| "epoch": 2.5953488372093023, |
| "grad_norm": 1.5193039178848267, |
| "learning_rate": 1.5015951622121896e-06, |
| "loss": 0.0435, |
| "mean_token_accuracy": 0.9854939579963684, |
| "step": 558 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 1.5376842021942139, |
| "learning_rate": 1.490470641152345e-06, |
| "loss": 0.0397, |
| "mean_token_accuracy": 0.9855803847312927, |
| "step": 559 |
| }, |
| { |
| "epoch": 2.604651162790698, |
| "grad_norm": 1.2507169246673584, |
| "learning_rate": 1.4794637549672182e-06, |
| "loss": 0.0394, |
| "mean_token_accuracy": 0.9875136017799377, |
| "step": 560 |
| }, |
| { |
| "epoch": 2.609302325581395, |
| "grad_norm": 2.15098237991333, |
| "learning_rate": 1.4685748265859043e-06, |
| "loss": 0.0272, |
| "mean_token_accuracy": 0.9911127090454102, |
| "step": 561 |
| }, |
| { |
| "epoch": 2.613953488372093, |
| "grad_norm": 1.8859761953353882, |
| "learning_rate": 1.457804175476751e-06, |
| "loss": 0.0417, |
| "mean_token_accuracy": 0.9860853552818298, |
| "step": 562 |
| }, |
| { |
| "epoch": 2.6186046511627907, |
| "grad_norm": 1.0621025562286377, |
| "learning_rate": 1.447152117637992e-06, |
| "loss": 0.029, |
| "mean_token_accuracy": 0.9893219470977783, |
| "step": 563 |
| }, |
| { |
| "epoch": 2.6232558139534885, |
| "grad_norm": 1.4596385955810547, |
| "learning_rate": 1.436618965588472e-06, |
| "loss": 0.0362, |
| "mean_token_accuracy": 0.9889196753501892, |
| "step": 564 |
| }, |
| { |
| "epoch": 2.6279069767441863, |
| "grad_norm": 1.2926936149597168, |
| "learning_rate": 1.4262050283584836e-06, |
| "loss": 0.0339, |
| "mean_token_accuracy": 0.9875206351280212, |
| "step": 565 |
| }, |
| { |
| "epoch": 2.6325581395348836, |
| "grad_norm": 1.6519856452941895, |
| "learning_rate": 1.4159106114806943e-06, |
| "loss": 0.0417, |
| "mean_token_accuracy": 0.9887183308601379, |
| "step": 566 |
| }, |
| { |
| "epoch": 2.6372093023255814, |
| "grad_norm": 1.3822687864303589, |
| "learning_rate": 1.4057360169811832e-06, |
| "loss": 0.0434, |
| "mean_token_accuracy": 0.9820433259010315, |
| "step": 567 |
| }, |
| { |
| "epoch": 2.641860465116279, |
| "grad_norm": 1.1875125169754028, |
| "learning_rate": 1.3956815433705861e-06, |
| "loss": 0.0314, |
| "mean_token_accuracy": 0.9890307784080505, |
| "step": 568 |
| }, |
| { |
| "epoch": 2.6465116279069765, |
| "grad_norm": 1.4650956392288208, |
| "learning_rate": 1.3857474856353299e-06, |
| "loss": 0.0386, |
| "mean_token_accuracy": 0.9873239398002625, |
| "step": 569 |
| }, |
| { |
| "epoch": 2.6511627906976747, |
| "grad_norm": 1.372135043144226, |
| "learning_rate": 1.3759341352289832e-06, |
| "loss": 0.04, |
| "mean_token_accuracy": 0.986075758934021, |
| "step": 570 |
| }, |
| { |
| "epoch": 2.655813953488372, |
| "grad_norm": 1.750218391418457, |
| "learning_rate": 1.3662417800637023e-06, |
| "loss": 0.045, |
| "mean_token_accuracy": 0.983469545841217, |
| "step": 571 |
| }, |
| { |
| "epoch": 2.66046511627907, |
| "grad_norm": 1.452467679977417, |
| "learning_rate": 1.3566707045017867e-06, |
| "loss": 0.0419, |
| "mean_token_accuracy": 0.9870980978012085, |
| "step": 572 |
| }, |
| { |
| "epoch": 2.6651162790697676, |
| "grad_norm": 1.6090556383132935, |
| "learning_rate": 1.3472211893473327e-06, |
| "loss": 0.0424, |
| "mean_token_accuracy": 0.9856728315353394, |
| "step": 573 |
| }, |
| { |
| "epoch": 2.669767441860465, |
| "grad_norm": 1.2582389116287231, |
| "learning_rate": 1.3378935118380004e-06, |
| "loss": 0.0362, |
| "mean_token_accuracy": 0.9885410070419312, |
| "step": 574 |
| }, |
| { |
| "epoch": 2.6744186046511627, |
| "grad_norm": 1.1907209157943726, |
| "learning_rate": 1.3286879456368746e-06, |
| "loss": 0.0362, |
| "mean_token_accuracy": 0.9901633858680725, |
| "step": 575 |
| }, |
| { |
| "epoch": 2.6790697674418604, |
| "grad_norm": 1.3772821426391602, |
| "learning_rate": 1.319604760824439e-06, |
| "loss": 0.0359, |
| "mean_token_accuracy": 0.9875583052635193, |
| "step": 576 |
| }, |
| { |
| "epoch": 2.683720930232558, |
| "grad_norm": 1.8042019605636597, |
| "learning_rate": 1.31064422389065e-06, |
| "loss": 0.0427, |
| "mean_token_accuracy": 0.9862815737724304, |
| "step": 577 |
| }, |
| { |
| "epoch": 2.688372093023256, |
| "grad_norm": 1.514086127281189, |
| "learning_rate": 1.3018065977271215e-06, |
| "loss": 0.04, |
| "mean_token_accuracy": 0.9870296120643616, |
| "step": 578 |
| }, |
| { |
| "epoch": 2.6930232558139533, |
| "grad_norm": 1.702939510345459, |
| "learning_rate": 1.293092141619407e-06, |
| "loss": 0.0425, |
| "mean_token_accuracy": 0.9871666431427002, |
| "step": 579 |
| }, |
| { |
| "epoch": 2.697674418604651, |
| "grad_norm": 1.2727701663970947, |
| "learning_rate": 1.2845011112394e-06, |
| "loss": 0.0283, |
| "mean_token_accuracy": 0.9897069334983826, |
| "step": 580 |
| }, |
| { |
| "epoch": 2.702325581395349, |
| "grad_norm": 1.6455163955688477, |
| "learning_rate": 1.276033758637823e-06, |
| "loss": 0.0434, |
| "mean_token_accuracy": 0.9873374104499817, |
| "step": 581 |
| }, |
| { |
| "epoch": 2.7069767441860466, |
| "grad_norm": 1.336192011833191, |
| "learning_rate": 1.2676903322368423e-06, |
| "loss": 0.0396, |
| "mean_token_accuracy": 0.9881370067596436, |
| "step": 582 |
| }, |
| { |
| "epoch": 2.7116279069767444, |
| "grad_norm": 1.4228109121322632, |
| "learning_rate": 1.2594710768227734e-06, |
| "loss": 0.0382, |
| "mean_token_accuracy": 0.9871864318847656, |
| "step": 583 |
| }, |
| { |
| "epoch": 2.7162790697674417, |
| "grad_norm": 1.6291853189468384, |
| "learning_rate": 1.2513762335389004e-06, |
| "loss": 0.0449, |
| "mean_token_accuracy": 0.9863990545272827, |
| "step": 584 |
| }, |
| { |
| "epoch": 2.7209302325581395, |
| "grad_norm": 1.453303337097168, |
| "learning_rate": 1.2434060398784039e-06, |
| "loss": 0.0382, |
| "mean_token_accuracy": 0.9885407090187073, |
| "step": 585 |
| }, |
| { |
| "epoch": 2.7255813953488373, |
| "grad_norm": 1.9516953229904175, |
| "learning_rate": 1.2355607296773896e-06, |
| "loss": 0.0518, |
| "mean_token_accuracy": 0.9837234616279602, |
| "step": 586 |
| }, |
| { |
| "epoch": 2.730232558139535, |
| "grad_norm": 1.5732613801956177, |
| "learning_rate": 1.2278405331080296e-06, |
| "loss": 0.0454, |
| "mean_token_accuracy": 0.9859471321105957, |
| "step": 587 |
| }, |
| { |
| "epoch": 2.734883720930233, |
| "grad_norm": 1.4327545166015625, |
| "learning_rate": 1.2202456766718092e-06, |
| "loss": 0.0406, |
| "mean_token_accuracy": 0.9854802489280701, |
| "step": 588 |
| }, |
| { |
| "epoch": 2.73953488372093, |
| "grad_norm": 1.2686004638671875, |
| "learning_rate": 1.212776383192883e-06, |
| "loss": 0.0377, |
| "mean_token_accuracy": 0.9876318573951721, |
| "step": 589 |
| }, |
| { |
| "epoch": 2.744186046511628, |
| "grad_norm": 1.2385032176971436, |
| "learning_rate": 1.2054328718115336e-06, |
| "loss": 0.0358, |
| "mean_token_accuracy": 0.9881836175918579, |
| "step": 590 |
| }, |
| { |
| "epoch": 2.7488372093023257, |
| "grad_norm": 1.3771368265151978, |
| "learning_rate": 1.1982153579777483e-06, |
| "loss": 0.0311, |
| "mean_token_accuracy": 0.9888147115707397, |
| "step": 591 |
| }, |
| { |
| "epoch": 2.753488372093023, |
| "grad_norm": 1.4716222286224365, |
| "learning_rate": 1.1911240534448899e-06, |
| "loss": 0.0415, |
| "mean_token_accuracy": 0.9859079718589783, |
| "step": 592 |
| }, |
| { |
| "epoch": 2.7581395348837208, |
| "grad_norm": 1.3605318069458008, |
| "learning_rate": 1.1841591662634943e-06, |
| "loss": 0.0387, |
| "mean_token_accuracy": 0.9877007007598877, |
| "step": 593 |
| }, |
| { |
| "epoch": 2.7627906976744185, |
| "grad_norm": 1.2023953199386597, |
| "learning_rate": 1.1773209007751562e-06, |
| "loss": 0.0356, |
| "mean_token_accuracy": 0.9872262477874756, |
| "step": 594 |
| }, |
| { |
| "epoch": 2.7674418604651163, |
| "grad_norm": 1.6226835250854492, |
| "learning_rate": 1.1706094576065416e-06, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9829424023628235, |
| "step": 595 |
| }, |
| { |
| "epoch": 2.772093023255814, |
| "grad_norm": 1.4002608060836792, |
| "learning_rate": 1.164025033663497e-06, |
| "loss": 0.0353, |
| "mean_token_accuracy": 0.9847367405891418, |
| "step": 596 |
| }, |
| { |
| "epoch": 2.7767441860465114, |
| "grad_norm": 1.3633453845977783, |
| "learning_rate": 1.1575678221252763e-06, |
| "loss": 0.0438, |
| "mean_token_accuracy": 0.9867115020751953, |
| "step": 597 |
| }, |
| { |
| "epoch": 2.781395348837209, |
| "grad_norm": 1.5677367448806763, |
| "learning_rate": 1.1512380124388695e-06, |
| "loss": 0.0463, |
| "mean_token_accuracy": 0.9877669811248779, |
| "step": 598 |
| }, |
| { |
| "epoch": 2.786046511627907, |
| "grad_norm": 1.2627447843551636, |
| "learning_rate": 1.1450357903134463e-06, |
| "loss": 0.0335, |
| "mean_token_accuracy": 0.9894976615905762, |
| "step": 599 |
| }, |
| { |
| "epoch": 2.7906976744186047, |
| "grad_norm": 1.5455451011657715, |
| "learning_rate": 1.1389613377149086e-06, |
| "loss": 0.0386, |
| "mean_token_accuracy": 0.9879539012908936, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.7953488372093025, |
| "grad_norm": 1.4009506702423096, |
| "learning_rate": 1.1330148328605484e-06, |
| "loss": 0.0427, |
| "mean_token_accuracy": 0.9870668053627014, |
| "step": 601 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 1.3464657068252563, |
| "learning_rate": 1.127196450213825e-06, |
| "loss": 0.0365, |
| "mean_token_accuracy": 0.987594485282898, |
| "step": 602 |
| }, |
| { |
| "epoch": 2.8046511627906976, |
| "grad_norm": 1.0960040092468262, |
| "learning_rate": 1.1215063604792396e-06, |
| "loss": 0.029, |
| "mean_token_accuracy": 0.9886877536773682, |
| "step": 603 |
| }, |
| { |
| "epoch": 2.8093023255813954, |
| "grad_norm": 1.5224353075027466, |
| "learning_rate": 1.1159447305973313e-06, |
| "loss": 0.0325, |
| "mean_token_accuracy": 0.9881473183631897, |
| "step": 604 |
| }, |
| { |
| "epoch": 2.813953488372093, |
| "grad_norm": 1.3734958171844482, |
| "learning_rate": 1.1105117237397777e-06, |
| "loss": 0.0353, |
| "mean_token_accuracy": 0.9883147478103638, |
| "step": 605 |
| }, |
| { |
| "epoch": 2.818604651162791, |
| "grad_norm": 1.2656145095825195, |
| "learning_rate": 1.1052074993046102e-06, |
| "loss": 0.0295, |
| "mean_token_accuracy": 0.9899190068244934, |
| "step": 606 |
| }, |
| { |
| "epoch": 2.8232558139534882, |
| "grad_norm": 1.465860366821289, |
| "learning_rate": 1.100032212911533e-06, |
| "loss": 0.0337, |
| "mean_token_accuracy": 0.9888620972633362, |
| "step": 607 |
| }, |
| { |
| "epoch": 2.827906976744186, |
| "grad_norm": 1.199744701385498, |
| "learning_rate": 1.0949860163973616e-06, |
| "loss": 0.0362, |
| "mean_token_accuracy": 0.9871125817298889, |
| "step": 608 |
| }, |
| { |
| "epoch": 2.832558139534884, |
| "grad_norm": 1.412898302078247, |
| "learning_rate": 1.0900690578115643e-06, |
| "loss": 0.039, |
| "mean_token_accuracy": 0.9859204888343811, |
| "step": 609 |
| }, |
| { |
| "epoch": 2.8372093023255816, |
| "grad_norm": 1.5508508682250977, |
| "learning_rate": 1.0852814814119238e-06, |
| "loss": 0.0381, |
| "mean_token_accuracy": 0.9879411458969116, |
| "step": 610 |
| }, |
| { |
| "epoch": 2.8418604651162793, |
| "grad_norm": 1.1056880950927734, |
| "learning_rate": 1.0806234276602984e-06, |
| "loss": 0.0256, |
| "mean_token_accuracy": 0.9905292391777039, |
| "step": 611 |
| }, |
| { |
| "epoch": 2.8465116279069766, |
| "grad_norm": 1.3313640356063843, |
| "learning_rate": 1.0760950332185055e-06, |
| "loss": 0.0396, |
| "mean_token_accuracy": 0.9873005747795105, |
| "step": 612 |
| }, |
| { |
| "epoch": 2.8511627906976744, |
| "grad_norm": 1.2394826412200928, |
| "learning_rate": 1.071696430944311e-06, |
| "loss": 0.0377, |
| "mean_token_accuracy": 0.9883508086204529, |
| "step": 613 |
| }, |
| { |
| "epoch": 2.855813953488372, |
| "grad_norm": 1.625504732131958, |
| "learning_rate": 1.0674277498875325e-06, |
| "loss": 0.0412, |
| "mean_token_accuracy": 0.9862161874771118, |
| "step": 614 |
| }, |
| { |
| "epoch": 2.8604651162790695, |
| "grad_norm": 1.3687355518341064, |
| "learning_rate": 1.0632891152862493e-06, |
| "loss": 0.0366, |
| "mean_token_accuracy": 0.9883472919464111, |
| "step": 615 |
| }, |
| { |
| "epoch": 2.8651162790697673, |
| "grad_norm": 1.2722115516662598, |
| "learning_rate": 1.0592806485631326e-06, |
| "loss": 0.0398, |
| "mean_token_accuracy": 0.98876953125, |
| "step": 616 |
| }, |
| { |
| "epoch": 2.869767441860465, |
| "grad_norm": 1.371472716331482, |
| "learning_rate": 1.0554024673218808e-06, |
| "loss": 0.038, |
| "mean_token_accuracy": 0.988584041595459, |
| "step": 617 |
| }, |
| { |
| "epoch": 2.874418604651163, |
| "grad_norm": 1.2753393650054932, |
| "learning_rate": 1.0516546853437686e-06, |
| "loss": 0.034, |
| "mean_token_accuracy": 0.9887096881866455, |
| "step": 618 |
| }, |
| { |
| "epoch": 2.8790697674418606, |
| "grad_norm": 1.1802083253860474, |
| "learning_rate": 1.0480374125843114e-06, |
| "loss": 0.0309, |
| "mean_token_accuracy": 0.9907568693161011, |
| "step": 619 |
| }, |
| { |
| "epoch": 2.883720930232558, |
| "grad_norm": 1.4220918416976929, |
| "learning_rate": 1.0445507551700356e-06, |
| "loss": 0.0351, |
| "mean_token_accuracy": 0.9894335865974426, |
| "step": 620 |
| }, |
| { |
| "epoch": 2.8883720930232557, |
| "grad_norm": 1.5494638681411743, |
| "learning_rate": 1.0411948153953696e-06, |
| "loss": 0.0432, |
| "mean_token_accuracy": 0.9865436553955078, |
| "step": 621 |
| }, |
| { |
| "epoch": 2.8930232558139535, |
| "grad_norm": 1.4016937017440796, |
| "learning_rate": 1.0379696917196378e-06, |
| "loss": 0.0437, |
| "mean_token_accuracy": 0.9852824807167053, |
| "step": 622 |
| }, |
| { |
| "epoch": 2.8976744186046512, |
| "grad_norm": 1.4522273540496826, |
| "learning_rate": 1.0348754787641751e-06, |
| "loss": 0.0327, |
| "mean_token_accuracy": 0.990084171295166, |
| "step": 623 |
| }, |
| { |
| "epoch": 2.902325581395349, |
| "grad_norm": 1.0468897819519043, |
| "learning_rate": 1.031912267309549e-06, |
| "loss": 0.028, |
| "mean_token_accuracy": 0.9912704825401306, |
| "step": 624 |
| }, |
| { |
| "epoch": 2.9069767441860463, |
| "grad_norm": 1.261525273323059, |
| "learning_rate": 1.029080144292899e-06, |
| "loss": 0.0305, |
| "mean_token_accuracy": 0.9909120202064514, |
| "step": 625 |
| }, |
| { |
| "epoch": 2.911627906976744, |
| "grad_norm": 1.5641429424285889, |
| "learning_rate": 1.026379192805382e-06, |
| "loss": 0.0392, |
| "mean_token_accuracy": 0.988041341304779, |
| "step": 626 |
| }, |
| { |
| "epoch": 2.916279069767442, |
| "grad_norm": 1.3897089958190918, |
| "learning_rate": 1.0238094920897374e-06, |
| "loss": 0.0376, |
| "mean_token_accuracy": 0.9882210493087769, |
| "step": 627 |
| }, |
| { |
| "epoch": 2.9209302325581397, |
| "grad_norm": 1.2228623628616333, |
| "learning_rate": 1.0213711175379614e-06, |
| "loss": 0.0319, |
| "mean_token_accuracy": 0.9905972480773926, |
| "step": 628 |
| }, |
| { |
| "epoch": 2.9255813953488374, |
| "grad_norm": 1.4966614246368408, |
| "learning_rate": 1.0190641406890946e-06, |
| "loss": 0.0329, |
| "mean_token_accuracy": 0.9902123808860779, |
| "step": 629 |
| }, |
| { |
| "epoch": 2.9302325581395348, |
| "grad_norm": 1.29335355758667, |
| "learning_rate": 1.0168886292271246e-06, |
| "loss": 0.0286, |
| "mean_token_accuracy": 0.9905264973640442, |
| "step": 630 |
| }, |
| { |
| "epoch": 2.9348837209302325, |
| "grad_norm": 1.2947627305984497, |
| "learning_rate": 1.0148446469789979e-06, |
| "loss": 0.0302, |
| "mean_token_accuracy": 0.9908397197723389, |
| "step": 631 |
| }, |
| { |
| "epoch": 2.9395348837209303, |
| "grad_norm": 1.5221575498580933, |
| "learning_rate": 1.0129322539127494e-06, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9851784706115723, |
| "step": 632 |
| }, |
| { |
| "epoch": 2.9441860465116276, |
| "grad_norm": 1.3887416124343872, |
| "learning_rate": 1.011151506135742e-06, |
| "loss": 0.0351, |
| "mean_token_accuracy": 0.9892547726631165, |
| "step": 633 |
| }, |
| { |
| "epoch": 2.948837209302326, |
| "grad_norm": 1.3253393173217773, |
| "learning_rate": 1.0095024558930204e-06, |
| "loss": 0.04, |
| "mean_token_accuracy": 0.9875065088272095, |
| "step": 634 |
| }, |
| { |
| "epoch": 2.953488372093023, |
| "grad_norm": 1.4894226789474487, |
| "learning_rate": 1.0079851515657794e-06, |
| "loss": 0.0497, |
| "mean_token_accuracy": 0.9831249713897705, |
| "step": 635 |
| }, |
| { |
| "epoch": 2.958139534883721, |
| "grad_norm": 1.3437986373901367, |
| "learning_rate": 1.006599637669943e-06, |
| "loss": 0.0414, |
| "mean_token_accuracy": 0.9876566529273987, |
| "step": 636 |
| }, |
| { |
| "epoch": 2.9627906976744187, |
| "grad_norm": 1.0954073667526245, |
| "learning_rate": 1.0053459548548582e-06, |
| "loss": 0.0305, |
| "mean_token_accuracy": 0.9911620020866394, |
| "step": 637 |
| }, |
| { |
| "epoch": 2.967441860465116, |
| "grad_norm": 1.5746396780014038, |
| "learning_rate": 1.004224139902105e-06, |
| "loss": 0.0437, |
| "mean_token_accuracy": 0.9854601621627808, |
| "step": 638 |
| }, |
| { |
| "epoch": 2.972093023255814, |
| "grad_norm": 1.400350570678711, |
| "learning_rate": 1.0032342257244139e-06, |
| "loss": 0.0383, |
| "mean_token_accuracy": 0.9862048029899597, |
| "step": 639 |
| }, |
| { |
| "epoch": 2.9767441860465116, |
| "grad_norm": 1.3652901649475098, |
| "learning_rate": 1.0023762413647023e-06, |
| "loss": 0.039, |
| "mean_token_accuracy": 0.9866381883621216, |
| "step": 640 |
| }, |
| { |
| "epoch": 2.9813953488372094, |
| "grad_norm": 1.742617130279541, |
| "learning_rate": 1.0016502119952224e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9840995669364929, |
| "step": 641 |
| }, |
| { |
| "epoch": 2.986046511627907, |
| "grad_norm": 1.3435075283050537, |
| "learning_rate": 1.0010561589168217e-06, |
| "loss": 0.0363, |
| "mean_token_accuracy": 0.9854980111122131, |
| "step": 642 |
| }, |
| { |
| "epoch": 2.9906976744186045, |
| "grad_norm": 1.7960363626480103, |
| "learning_rate": 1.0005940995583183e-06, |
| "loss": 0.0452, |
| "mean_token_accuracy": 0.9852866530418396, |
| "step": 643 |
| }, |
| { |
| "epoch": 2.9953488372093022, |
| "grad_norm": 1.5572556257247925, |
| "learning_rate": 1.0002640474759911e-06, |
| "loss": 0.0327, |
| "mean_token_accuracy": 0.9882596731185913, |
| "step": 644 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.6895026564598083, |
| "learning_rate": 1.0000660123531788e-06, |
| "loss": 0.0115, |
| "mean_token_accuracy": 0.997201144695282, |
| "step": 645 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 645, |
| "total_flos": 6.064391158811853e+17, |
| "train_loss": 0.013678103204556676, |
| "train_runtime": 808.3613, |
| "train_samples_per_second": 25.426, |
| "train_steps_per_second": 0.798 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 645, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.064391158811853e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
