| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 124, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008064516129032258, | |
| "grad_norm": 82.1250991821289, | |
| "learning_rate": 4.999197688241076e-07, | |
| "loss": 3.3188, | |
| "mean_token_accuracy": 0.4619899392127991, | |
| "num_tokens": 3582.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016129032258064516, | |
| "grad_norm": 85.84162139892578, | |
| "learning_rate": 4.996791267927632e-07, | |
| "loss": 3.1019, | |
| "mean_token_accuracy": 0.48747536540031433, | |
| "num_tokens": 7139.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024193548387096774, | |
| "grad_norm": 77.11351776123047, | |
| "learning_rate": 4.992782283619118e-07, | |
| "loss": 3.0994, | |
| "mean_token_accuracy": 0.46798279881477356, | |
| "num_tokens": 11094.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03225806451612903, | |
| "grad_norm": 74.11935424804688, | |
| "learning_rate": 4.987173308479737e-07, | |
| "loss": 3.0893, | |
| "mean_token_accuracy": 0.4673512279987335, | |
| "num_tokens": 14896.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04032258064516129, | |
| "grad_norm": 58.4622917175293, | |
| "learning_rate": 4.979967942626857e-07, | |
| "loss": 2.9759, | |
| "mean_token_accuracy": 0.4749932289123535, | |
| "num_tokens": 18599.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04838709677419355, | |
| "grad_norm": 71.54608154296875, | |
| "learning_rate": 4.971170810820278e-07, | |
| "loss": 2.8627, | |
| "mean_token_accuracy": 0.489130437374115, | |
| "num_tokens": 22099.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.056451612903225805, | |
| "grad_norm": 67.31790924072266, | |
| "learning_rate": 4.960787559493836e-07, | |
| "loss": 2.9878, | |
| "mean_token_accuracy": 0.49747729301452637, | |
| "num_tokens": 25076.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 51.87714767456055, | |
| "learning_rate": 4.948824853131236e-07, | |
| "loss": 2.8431, | |
| "mean_token_accuracy": 0.4804079532623291, | |
| "num_tokens": 28806.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07258064516129033, | |
| "grad_norm": 50.492496490478516, | |
| "learning_rate": 4.935290369988468e-07, | |
| "loss": 2.7265, | |
| "mean_token_accuracy": 0.4897351861000061, | |
| "num_tokens": 32171.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08064516129032258, | |
| "grad_norm": 50.19187927246094, | |
| "learning_rate": 4.920192797165511e-07, | |
| "loss": 2.5757, | |
| "mean_token_accuracy": 0.5013927817344666, | |
| "num_tokens": 35765.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08870967741935484, | |
| "grad_norm": 53.92109298706055, | |
| "learning_rate": 4.903541825030531e-07, | |
| "loss": 2.5328, | |
| "mean_token_accuracy": 0.5096573233604431, | |
| "num_tokens": 38979.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0967741935483871, | |
| "grad_norm": 131.06643676757812, | |
| "learning_rate": 4.885348141000122e-07, | |
| "loss": 2.4167, | |
| "mean_token_accuracy": 0.507402777671814, | |
| "num_tokens": 42968.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10483870967741936, | |
| "grad_norm": 42.45437240600586, | |
| "learning_rate": 4.865623422679592e-07, | |
| "loss": 2.3694, | |
| "mean_token_accuracy": 0.5128635168075562, | |
| "num_tokens": 46548.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11290322580645161, | |
| "grad_norm": 40.65642547607422, | |
| "learning_rate": 4.844380330367701e-07, | |
| "loss": 2.2659, | |
| "mean_token_accuracy": 0.5277366042137146, | |
| "num_tokens": 49923.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12096774193548387, | |
| "grad_norm": 40.563663482666016, | |
| "learning_rate": 4.821632498930656e-07, | |
| "loss": 2.325, | |
| "mean_token_accuracy": 0.5243242979049683, | |
| "num_tokens": 53257.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 29.71602439880371, | |
| "learning_rate": 4.797394529050577e-07, | |
| "loss": 2.2635, | |
| "mean_token_accuracy": 0.5110940933227539, | |
| "num_tokens": 57182.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13709677419354838, | |
| "grad_norm": 36.85178756713867, | |
| "learning_rate": 4.771681977854062e-07, | |
| "loss": 2.2947, | |
| "mean_token_accuracy": 0.49719932675361633, | |
| "num_tokens": 60221.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14516129032258066, | |
| "grad_norm": 40.669857025146484, | |
| "learning_rate": 4.744511348926854e-07, | |
| "loss": 2.1618, | |
| "mean_token_accuracy": 0.5076530575752258, | |
| "num_tokens": 63753.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1532258064516129, | |
| "grad_norm": 31.07614517211914, | |
| "learning_rate": 4.7159000817210204e-07, | |
| "loss": 2.2338, | |
| "mean_token_accuracy": 0.5, | |
| "num_tokens": 67491.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16129032258064516, | |
| "grad_norm": 39.705753326416016, | |
| "learning_rate": 4.685866540361455e-07, | |
| "loss": 2.1938, | |
| "mean_token_accuracy": 0.5107913613319397, | |
| "num_tokens": 70831.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1693548387096774, | |
| "grad_norm": 40.17426681518555, | |
| "learning_rate": 4.654430001858874e-07, | |
| "loss": 2.1139, | |
| "mean_token_accuracy": 0.5218411087989807, | |
| "num_tokens": 74246.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1774193548387097, | |
| "grad_norm": 34.13058853149414, | |
| "learning_rate": 4.6216106437368775e-07, | |
| "loss": 2.0303, | |
| "mean_token_accuracy": 0.5338891744613647, | |
| "num_tokens": 77968.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18548387096774194, | |
| "grad_norm": 25.600557327270508, | |
| "learning_rate": 4.5874295310810185e-07, | |
| "loss": 2.0356, | |
| "mean_token_accuracy": 0.515510618686676, | |
| "num_tokens": 80841.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 14.962992668151855, | |
| "learning_rate": 4.551908603018191e-07, | |
| "loss": 1.9918, | |
| "mean_token_accuracy": 0.5420023202896118, | |
| "num_tokens": 84321.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20161290322580644, | |
| "grad_norm": 10.336100578308105, | |
| "learning_rate": 4.5150706586350127e-07, | |
| "loss": 2.0338, | |
| "mean_token_accuracy": 0.5391054153442383, | |
| "num_tokens": 88148.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20967741935483872, | |
| "grad_norm": 11.232644081115723, | |
| "learning_rate": 4.476939342344246e-07, | |
| "loss": 2.0344, | |
| "mean_token_accuracy": 0.5330302119255066, | |
| "num_tokens": 91891.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21774193548387097, | |
| "grad_norm": 8.730783462524414, | |
| "learning_rate": 4.437539128708647e-07, | |
| "loss": 2.0291, | |
| "mean_token_accuracy": 0.5340464115142822, | |
| "num_tokens": 95728.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22580645161290322, | |
| "grad_norm": 9.901666641235352, | |
| "learning_rate": 4.396895306731977e-07, | |
| "loss": 1.9593, | |
| "mean_token_accuracy": 0.5452925562858582, | |
| "num_tokens": 99099.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23387096774193547, | |
| "grad_norm": 8.69468879699707, | |
| "learning_rate": 4.355033963627277e-07, | |
| "loss": 1.9023, | |
| "mean_token_accuracy": 0.5690703988075256, | |
| "num_tokens": 102556.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24193548387096775, | |
| "grad_norm": 8.984487533569336, | |
| "learning_rate": 4.3119819680727996e-07, | |
| "loss": 1.938, | |
| "mean_token_accuracy": 0.5465425252914429, | |
| "num_tokens": 106320.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 9.061673164367676, | |
| "learning_rate": 4.2677669529663686e-07, | |
| "loss": 1.9321, | |
| "mean_token_accuracy": 0.5477131605148315, | |
| "num_tokens": 109866.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 8.572089195251465, | |
| "learning_rate": 4.2224172976892166e-07, | |
| "loss": 1.9352, | |
| "mean_token_accuracy": 0.5485040545463562, | |
| "num_tokens": 113179.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2661290322580645, | |
| "grad_norm": 8.716224670410156, | |
| "learning_rate": 4.175962109890696e-07, | |
| "loss": 1.8432, | |
| "mean_token_accuracy": 0.550000011920929, | |
| "num_tokens": 116683.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.27419354838709675, | |
| "grad_norm": 11.871490478515625, | |
| "learning_rate": 4.128431206805556e-07, | |
| "loss": 1.8008, | |
| "mean_token_accuracy": 0.5759973526000977, | |
| "num_tokens": 119720.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.28225806451612906, | |
| "grad_norm": 9.3665132522583, | |
| "learning_rate": 4.0798550961157595e-07, | |
| "loss": 1.8901, | |
| "mean_token_accuracy": 0.552654504776001, | |
| "num_tokens": 123171.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2903225806451613, | |
| "grad_norm": 9.704719543457031, | |
| "learning_rate": 4.030264956369157e-07, | |
| "loss": 1.8121, | |
| "mean_token_accuracy": 0.5599347352981567, | |
| "num_tokens": 126854.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.29838709677419356, | |
| "grad_norm": 10.195917129516602, | |
| "learning_rate": 3.9796926169675424e-07, | |
| "loss": 1.885, | |
| "mean_token_accuracy": 0.5533230304718018, | |
| "num_tokens": 130740.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3064516129032258, | |
| "grad_norm": 9.518072128295898, | |
| "learning_rate": 3.9281705377369805e-07, | |
| "loss": 1.9059, | |
| "mean_token_accuracy": 0.5531600713729858, | |
| "num_tokens": 134130.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.31451612903225806, | |
| "grad_norm": 7.841033458709717, | |
| "learning_rate": 3.875731788093478e-07, | |
| "loss": 1.8547, | |
| "mean_token_accuracy": 0.5586956739425659, | |
| "num_tokens": 137814.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 10.610803604125977, | |
| "learning_rate": 3.822410025817406e-07, | |
| "loss": 1.8147, | |
| "mean_token_accuracy": 0.5637563467025757, | |
| "num_tokens": 141151.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33064516129032256, | |
| "grad_norm": 10.157751083374023, | |
| "learning_rate": 3.768239475450268e-07, | |
| "loss": 1.8701, | |
| "mean_token_accuracy": 0.549227237701416, | |
| "num_tokens": 144649.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3387096774193548, | |
| "grad_norm": 8.627851486206055, | |
| "learning_rate": 3.713254906327703e-07, | |
| "loss": 1.8508, | |
| "mean_token_accuracy": 0.557908833026886, | |
| "num_tokens": 148383.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3467741935483871, | |
| "grad_norm": 7.615920543670654, | |
| "learning_rate": 3.657491610262802e-07, | |
| "loss": 1.8584, | |
| "mean_token_accuracy": 0.5659451484680176, | |
| "num_tokens": 151852.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3548387096774194, | |
| "grad_norm": 8.200079917907715, | |
| "learning_rate": 3.6009853788940856e-07, | |
| "loss": 1.7812, | |
| "mean_token_accuracy": 0.5586913228034973, | |
| "num_tokens": 155860.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3629032258064516, | |
| "grad_norm": 7.837497234344482, | |
| "learning_rate": 3.543772480712658e-07, | |
| "loss": 1.7635, | |
| "mean_token_accuracy": 0.5686478018760681, | |
| "num_tokens": 159717.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3709677419354839, | |
| "grad_norm": 8.181253433227539, | |
| "learning_rate": 3.4858896377832965e-07, | |
| "loss": 1.7004, | |
| "mean_token_accuracy": 0.5794797539710999, | |
| "num_tokens": 163181.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3790322580645161, | |
| "grad_norm": 6.781255722045898, | |
| "learning_rate": 3.42737400217442e-07, | |
| "loss": 1.8779, | |
| "mean_token_accuracy": 0.5520778298377991, | |
| "num_tokens": 166987.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 7.666635036468506, | |
| "learning_rate": 3.36826313211205e-07, | |
| "loss": 1.8343, | |
| "mean_token_accuracy": 0.5685471296310425, | |
| "num_tokens": 170164.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3951612903225806, | |
| "grad_norm": 8.650765419006348, | |
| "learning_rate": 3.308594967873095e-07, | |
| "loss": 1.7022, | |
| "mean_token_accuracy": 0.5841107368469238, | |
| "num_tokens": 173491.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4032258064516129, | |
| "grad_norm": 7.792832851409912, | |
| "learning_rate": 3.2484078074333956e-07, | |
| "loss": 1.7076, | |
| "mean_token_accuracy": 0.5851721167564392, | |
| "num_tokens": 176894.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4112903225806452, | |
| "grad_norm": 9.63578987121582, | |
| "learning_rate": 3.1877402818861946e-07, | |
| "loss": 1.7369, | |
| "mean_token_accuracy": 0.576729416847229, | |
| "num_tokens": 180671.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.41935483870967744, | |
| "grad_norm": 7.068120002746582, | |
| "learning_rate": 3.126631330646801e-07, | |
| "loss": 1.7723, | |
| "mean_token_accuracy": 0.5763046741485596, | |
| "num_tokens": 184220.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4274193548387097, | |
| "grad_norm": 7.844783782958984, | |
| "learning_rate": 3.065120176459337e-07, | |
| "loss": 1.7888, | |
| "mean_token_accuracy": 0.5663133859634399, | |
| "num_tokens": 187715.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.43548387096774194, | |
| "grad_norm": 6.963573932647705, | |
| "learning_rate": 3.00324630022165e-07, | |
| "loss": 1.6962, | |
| "mean_token_accuracy": 0.5830934047698975, | |
| "num_tokens": 191540.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4435483870967742, | |
| "grad_norm": 7.507209777832031, | |
| "learning_rate": 2.9410494156445216e-07, | |
| "loss": 1.7422, | |
| "mean_token_accuracy": 0.5805253982543945, | |
| "num_tokens": 195046.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.45161290322580644, | |
| "grad_norm": 7.959713459014893, | |
| "learning_rate": 2.8785694437614416e-07, | |
| "loss": 1.7368, | |
| "mean_token_accuracy": 0.5760632753372192, | |
| "num_tokens": 198718.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4596774193548387, | |
| "grad_norm": 7.953831195831299, | |
| "learning_rate": 2.8158464873053234e-07, | |
| "loss": 1.7707, | |
| "mean_token_accuracy": 0.5705274939537048, | |
| "num_tokens": 202210.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.46774193548387094, | |
| "grad_norm": 8.072004318237305, | |
| "learning_rate": 2.7529208049685804e-07, | |
| "loss": 1.7197, | |
| "mean_token_accuracy": 0.5858024954795837, | |
| "num_tokens": 205454.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.47580645161290325, | |
| "grad_norm": 8.691699028015137, | |
| "learning_rate": 2.6898327855631154e-07, | |
| "loss": 1.807, | |
| "mean_token_accuracy": 0.560819149017334, | |
| "num_tokens": 209511.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 6.996568202972412, | |
| "learning_rate": 2.626622922096782e-07, | |
| "loss": 1.7697, | |
| "mean_token_accuracy": 0.5675398111343384, | |
| "num_tokens": 213409.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49193548387096775, | |
| "grad_norm": 8.156956672668457, | |
| "learning_rate": 2.5633317857829693e-07, | |
| "loss": 1.6853, | |
| "mean_token_accuracy": 0.5745296478271484, | |
| "num_tokens": 216868.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 8.733380317687988, | |
| "learning_rate": 2.5e-07, | |
| "loss": 1.6566, | |
| "mean_token_accuracy": 0.5956632494926453, | |
| "num_tokens": 220008.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5080645161290323, | |
| "grad_norm": 6.773242473602295, | |
| "learning_rate": 2.4366682142170305e-07, | |
| "loss": 1.7601, | |
| "mean_token_accuracy": 0.5683262944221497, | |
| "num_tokens": 223788.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 6.594358444213867, | |
| "learning_rate": 2.3733770779032184e-07, | |
| "loss": 1.754, | |
| "mean_token_accuracy": 0.5651482939720154, | |
| "num_tokens": 227568.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5241935483870968, | |
| "grad_norm": 7.253048419952393, | |
| "learning_rate": 2.3101672144368846e-07, | |
| "loss": 1.7411, | |
| "mean_token_accuracy": 0.5777088403701782, | |
| "num_tokens": 231439.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.532258064516129, | |
| "grad_norm": 6.758819580078125, | |
| "learning_rate": 2.2470791950314196e-07, | |
| "loss": 1.6841, | |
| "mean_token_accuracy": 0.583798885345459, | |
| "num_tokens": 235023.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5403225806451613, | |
| "grad_norm": 7.620910167694092, | |
| "learning_rate": 2.1841535126946775e-07, | |
| "loss": 1.7435, | |
| "mean_token_accuracy": 0.5806363224983215, | |
| "num_tokens": 238673.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5483870967741935, | |
| "grad_norm": 7.808475017547607, | |
| "learning_rate": 2.121430556238559e-07, | |
| "loss": 1.7878, | |
| "mean_token_accuracy": 0.5660945773124695, | |
| "num_tokens": 241998.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5564516129032258, | |
| "grad_norm": 10.025287628173828, | |
| "learning_rate": 2.0589505843554795e-07, | |
| "loss": 1.8058, | |
| "mean_token_accuracy": 0.566918134689331, | |
| "num_tokens": 245581.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5645161290322581, | |
| "grad_norm": 7.763560771942139, | |
| "learning_rate": 1.9967536997783493e-07, | |
| "loss": 1.6668, | |
| "mean_token_accuracy": 0.5830458402633667, | |
| "num_tokens": 249643.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5725806451612904, | |
| "grad_norm": 7.218297958374023, | |
| "learning_rate": 1.9348798235406626e-07, | |
| "loss": 1.6796, | |
| "mean_token_accuracy": 0.5924479365348816, | |
| "num_tokens": 253487.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 7.534745693206787, | |
| "learning_rate": 1.8733686693531982e-07, | |
| "loss": 1.6667, | |
| "mean_token_accuracy": 0.5781828761100769, | |
| "num_tokens": 257002.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5887096774193549, | |
| "grad_norm": 9.321051597595215, | |
| "learning_rate": 1.8122597181138047e-07, | |
| "loss": 1.6971, | |
| "mean_token_accuracy": 0.5793435573577881, | |
| "num_tokens": 260327.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5967741935483871, | |
| "grad_norm": 7.620558261871338, | |
| "learning_rate": 1.751592192566605e-07, | |
| "loss": 1.8091, | |
| "mean_token_accuracy": 0.5647743940353394, | |
| "num_tokens": 263766.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6048387096774194, | |
| "grad_norm": 6.960766315460205, | |
| "learning_rate": 1.6914050321269047e-07, | |
| "loss": 1.7232, | |
| "mean_token_accuracy": 0.5714285969734192, | |
| "num_tokens": 267431.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6129032258064516, | |
| "grad_norm": 8.637341499328613, | |
| "learning_rate": 1.6317368678879496e-07, | |
| "loss": 1.8332, | |
| "mean_token_accuracy": 0.5513805747032166, | |
| "num_tokens": 270948.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6209677419354839, | |
| "grad_norm": 6.999222278594971, | |
| "learning_rate": 1.5726259978255807e-07, | |
| "loss": 1.737, | |
| "mean_token_accuracy": 0.578661322593689, | |
| "num_tokens": 274448.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6290322580645161, | |
| "grad_norm": 6.716799736022949, | |
| "learning_rate": 1.514110362216704e-07, | |
| "loss": 1.5999, | |
| "mean_token_accuracy": 0.6048541069030762, | |
| "num_tokens": 278119.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6370967741935484, | |
| "grad_norm": 7.0507659912109375, | |
| "learning_rate": 1.4562275192873428e-07, | |
| "loss": 1.7363, | |
| "mean_token_accuracy": 0.5828737020492554, | |
| "num_tokens": 281568.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 8.561986923217773, | |
| "learning_rate": 1.3990146211059139e-07, | |
| "loss": 1.6661, | |
| "mean_token_accuracy": 0.591465175151825, | |
| "num_tokens": 285087.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6532258064516129, | |
| "grad_norm": 7.29276704788208, | |
| "learning_rate": 1.342508389737198e-07, | |
| "loss": 1.6752, | |
| "mean_token_accuracy": 0.5835070013999939, | |
| "num_tokens": 288450.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.6612903225806451, | |
| "grad_norm": 7.706023216247559, | |
| "learning_rate": 1.2867450936722978e-07, | |
| "loss": 1.7451, | |
| "mean_token_accuracy": 0.5716311931610107, | |
| "num_tokens": 291979.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.6693548387096774, | |
| "grad_norm": 7.056520462036133, | |
| "learning_rate": 1.2317605245497323e-07, | |
| "loss": 1.7154, | |
| "mean_token_accuracy": 0.5758506059646606, | |
| "num_tokens": 295892.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.6774193548387096, | |
| "grad_norm": 7.503317356109619, | |
| "learning_rate": 1.1775899741825945e-07, | |
| "loss": 1.6899, | |
| "mean_token_accuracy": 0.5809495449066162, | |
| "num_tokens": 299287.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.6854838709677419, | |
| "grad_norm": 6.785901069641113, | |
| "learning_rate": 1.1242682119065216e-07, | |
| "loss": 1.7004, | |
| "mean_token_accuracy": 0.5904300808906555, | |
| "num_tokens": 302802.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6935483870967742, | |
| "grad_norm": 8.526169776916504, | |
| "learning_rate": 1.0718294622630186e-07, | |
| "loss": 1.764, | |
| "mean_token_accuracy": 0.5716612339019775, | |
| "num_tokens": 305876.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7016129032258065, | |
| "grad_norm": 8.141705513000488, | |
| "learning_rate": 1.0203073830324565e-07, | |
| "loss": 1.6696, | |
| "mean_token_accuracy": 0.5959654450416565, | |
| "num_tokens": 309350.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7096774193548387, | |
| "grad_norm": 7.417829513549805, | |
| "learning_rate": 9.697350436308427e-08, | |
| "loss": 1.6542, | |
| "mean_token_accuracy": 0.5915982127189636, | |
| "num_tokens": 312520.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.717741935483871, | |
| "grad_norm": 7.390657424926758, | |
| "learning_rate": 9.201449038842401e-08, | |
| "loss": 1.7805, | |
| "mean_token_accuracy": 0.5598756074905396, | |
| "num_tokens": 316382.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7258064516129032, | |
| "grad_norm": 7.71380615234375, | |
| "learning_rate": 8.715687931944449e-08, | |
| "loss": 1.6886, | |
| "mean_token_accuracy": 0.578542947769165, | |
| "num_tokens": 319900.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7338709677419355, | |
| "grad_norm": 7.551061153411865, | |
| "learning_rate": 8.240378901093034e-08, | |
| "loss": 1.7469, | |
| "mean_token_accuracy": 0.570781409740448, | |
| "num_tokens": 323436.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7419354838709677, | |
| "grad_norm": 9.389298439025879, | |
| "learning_rate": 7.775827023107834e-08, | |
| "loss": 1.7162, | |
| "mean_token_accuracy": 0.571618914604187, | |
| "num_tokens": 326442.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 7.125860691070557, | |
| "learning_rate": 7.322330470336313e-08, | |
| "loss": 1.7112, | |
| "mean_token_accuracy": 0.568901777267456, | |
| "num_tokens": 330234.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.7580645161290323, | |
| "grad_norm": 7.604709148406982, | |
| "learning_rate": 6.880180319272006e-08, | |
| "loss": 1.653, | |
| "mean_token_accuracy": 0.5836288928985596, | |
| "num_tokens": 333903.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.7661290322580645, | |
| "grad_norm": 6.952591896057129, | |
| "learning_rate": 6.449660363727236e-08, | |
| "loss": 1.6965, | |
| "mean_token_accuracy": 0.5798975825309753, | |
| "num_tokens": 337618.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 10.35627555847168, | |
| "learning_rate": 6.031046932680229e-08, | |
| "loss": 1.6945, | |
| "mean_token_accuracy": 0.5744901299476624, | |
| "num_tokens": 340515.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.782258064516129, | |
| "grad_norm": 7.425570487976074, | |
| "learning_rate": 5.624608712913531e-08, | |
| "loss": 1.6154, | |
| "mean_token_accuracy": 0.5917431116104126, | |
| "num_tokens": 344007.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.7903225806451613, | |
| "grad_norm": 10.059042930603027, | |
| "learning_rate": 5.230606576557539e-08, | |
| "loss": 1.6855, | |
| "mean_token_accuracy": 0.5853906869888306, | |
| "num_tokens": 347940.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.7983870967741935, | |
| "grad_norm": 6.582756042480469, | |
| "learning_rate": 4.84929341364988e-08, | |
| "loss": 1.6939, | |
| "mean_token_accuracy": 0.5809850096702576, | |
| "num_tokens": 351741.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8064516129032258, | |
| "grad_norm": 6.744507312774658, | |
| "learning_rate": 4.480913969818098e-08, | |
| "loss": 1.6739, | |
| "mean_token_accuracy": 0.585814356803894, | |
| "num_tokens": 355171.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8145161290322581, | |
| "grad_norm": 6.796554088592529, | |
| "learning_rate": 4.125704689189818e-08, | |
| "loss": 1.7039, | |
| "mean_token_accuracy": 0.5784457325935364, | |
| "num_tokens": 359267.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8225806451612904, | |
| "grad_norm": 6.474706649780273, | |
| "learning_rate": 3.783893562631224e-08, | |
| "loss": 1.6828, | |
| "mean_token_accuracy": 0.5838965773582458, | |
| "num_tokens": 362674.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.8306451612903226, | |
| "grad_norm": 7.683028221130371, | |
| "learning_rate": 3.455699981411259e-08, | |
| "loss": 1.7309, | |
| "mean_token_accuracy": 0.5660528540611267, | |
| "num_tokens": 366425.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.8387096774193549, | |
| "grad_norm": 7.123412609100342, | |
| "learning_rate": 3.141334596385447e-08, | |
| "loss": 1.6526, | |
| "mean_token_accuracy": 0.5894578099250793, | |
| "num_tokens": 369749.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.8467741935483871, | |
| "grad_norm": 6.300046920776367, | |
| "learning_rate": 2.8409991827897968e-08, | |
| "loss": 1.6927, | |
| "mean_token_accuracy": 0.5794023275375366, | |
| "num_tokens": 373802.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8548387096774194, | |
| "grad_norm": 6.947690486907959, | |
| "learning_rate": 2.5548865107314604e-08, | |
| "loss": 1.7412, | |
| "mean_token_accuracy": 0.5656623244285583, | |
| "num_tokens": 377324.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.8629032258064516, | |
| "grad_norm": 7.4605231285095215, | |
| "learning_rate": 2.283180221459377e-08, | |
| "loss": 1.7679, | |
| "mean_token_accuracy": 0.5644617676734924, | |
| "num_tokens": 381183.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.8709677419354839, | |
| "grad_norm": 6.687449932098389, | |
| "learning_rate": 2.0260547094942348e-08, | |
| "loss": 1.7144, | |
| "mean_token_accuracy": 0.5790040493011475, | |
| "num_tokens": 384902.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.8790322580645161, | |
| "grad_norm": 9.971823692321777, | |
| "learning_rate": 1.7836750106934474e-08, | |
| "loss": 1.6716, | |
| "mean_token_accuracy": 0.5851125121116638, | |
| "num_tokens": 388372.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.8870967741935484, | |
| "grad_norm": 8.792091369628906, | |
| "learning_rate": 1.5561966963229923e-08, | |
| "loss": 1.66, | |
| "mean_token_accuracy": 0.5835981965065002, | |
| "num_tokens": 391522.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8951612903225806, | |
| "grad_norm": 7.2787981033325195, | |
| "learning_rate": 1.3437657732040781e-08, | |
| "loss": 1.6463, | |
| "mean_token_accuracy": 0.5921754837036133, | |
| "num_tokens": 394900.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 7.135777473449707, | |
| "learning_rate": 1.1465185899987794e-08, | |
| "loss": 1.7416, | |
| "mean_token_accuracy": 0.5735452771186829, | |
| "num_tokens": 398616.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9112903225806451, | |
| "grad_norm": 8.646471977233887, | |
| "learning_rate": 9.6458174969469e-09, | |
| "loss": 1.7218, | |
| "mean_token_accuracy": 0.5801047086715698, | |
| "num_tokens": 402440.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9193548387096774, | |
| "grad_norm": 6.620112895965576, | |
| "learning_rate": 7.980720283448955e-09, | |
| "loss": 1.8393, | |
| "mean_token_accuracy": 0.5539906024932861, | |
| "num_tokens": 406278.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9274193548387096, | |
| "grad_norm": 8.354401588439941, | |
| "learning_rate": 6.470963001153268e-09, | |
| "loss": 1.7239, | |
| "mean_token_accuracy": 0.5888278484344482, | |
| "num_tokens": 409558.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9354838709677419, | |
| "grad_norm": 7.131601810455322, | |
| "learning_rate": 5.117514686876378e-09, | |
| "loss": 1.6136, | |
| "mean_token_accuracy": 0.5943509340286255, | |
| "num_tokens": 412890.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.9435483870967742, | |
| "grad_norm": 7.938460826873779, | |
| "learning_rate": 3.921244050616446e-09, | |
| "loss": 1.7333, | |
| "mean_token_accuracy": 0.5793216824531555, | |
| "num_tokens": 416550.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.9516129032258065, | |
| "grad_norm": 7.657175540924072, | |
| "learning_rate": 2.8829189179721547e-09, | |
| "loss": 1.7309, | |
| "mean_token_accuracy": 0.5766178369522095, | |
| "num_tokens": 419830.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.9596774193548387, | |
| "grad_norm": 7.384486198425293, | |
| "learning_rate": 2.0032057373142453e-09, | |
| "loss": 1.6211, | |
| "mean_token_accuracy": 0.5845938324928284, | |
| "num_tokens": 423404.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 8.56894588470459, | |
| "learning_rate": 1.2826691520262112e-09, | |
| "loss": 1.7963, | |
| "mean_token_accuracy": 0.57413250207901, | |
| "num_tokens": 426895.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9758064516129032, | |
| "grad_norm": 6.813057899475098, | |
| "learning_rate": 7.217716380881477e-10, | |
| "loss": 1.726, | |
| "mean_token_accuracy": 0.5653586387634277, | |
| "num_tokens": 430900.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.9838709677419355, | |
| "grad_norm": 6.8685431480407715, | |
| "learning_rate": 3.2087320723681033e-10, | |
| "loss": 1.6799, | |
| "mean_token_accuracy": 0.5889589190483093, | |
| "num_tokens": 434237.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.9919354838709677, | |
| "grad_norm": 7.024580955505371, | |
| "learning_rate": 8.023117589237016e-11, | |
| "loss": 1.7037, | |
| "mean_token_accuracy": 0.5847502946853638, | |
| "num_tokens": 438005.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.294002532958984, | |
| "learning_rate": 0.0, | |
| "loss": 1.6386, | |
| "mean_token_accuracy": 0.5888568758964539, | |
| "num_tokens": 441132.0, | |
| "step": 124 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 124, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0678265542868992e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |