| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.96, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.43850863675276436, |
| "epoch": 0.0096, |
| "grad_norm": 4.34375, |
| "learning_rate": 1e-06, |
| "loss": 0.5373, |
| "mean_token_accuracy": 0.8229872425397237, |
| "num_tokens": 3432459.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.43693508704503375, |
| "epoch": 0.0192, |
| "grad_norm": 2.8125, |
| "learning_rate": 1e-06, |
| "loss": 0.506, |
| "mean_token_accuracy": 0.8290777782599131, |
| "num_tokens": 6859685.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.44068048397699994, |
| "epoch": 0.0288, |
| "grad_norm": 2.421875, |
| "learning_rate": 1e-06, |
| "loss": 0.4912, |
| "mean_token_accuracy": 0.8306132018566131, |
| "num_tokens": 10280810.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.4448391616344452, |
| "epoch": 0.0384, |
| "grad_norm": 1.8203125, |
| "learning_rate": 1e-06, |
| "loss": 0.4852, |
| "mean_token_accuracy": 0.8322072466214497, |
| "num_tokens": 13708851.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.4470527251561483, |
| "epoch": 0.048, |
| "grad_norm": 1.2734375, |
| "learning_rate": 1e-06, |
| "loss": 0.4798, |
| "mean_token_accuracy": 0.8338870048522949, |
| "num_tokens": 17136948.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.44311814606189726, |
| "epoch": 0.0576, |
| "grad_norm": 1.203125, |
| "learning_rate": 1e-06, |
| "loss": 0.4701, |
| "mean_token_accuracy": 0.8359324594338735, |
| "num_tokens": 20560658.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.4470181296269099, |
| "epoch": 0.0672, |
| "grad_norm": 1.1640625, |
| "learning_rate": 1e-06, |
| "loss": 0.4702, |
| "mean_token_accuracy": 0.8356486141681672, |
| "num_tokens": 23987248.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.449398942788442, |
| "epoch": 0.0768, |
| "grad_norm": 0.9296875, |
| "learning_rate": 1e-06, |
| "loss": 0.47, |
| "mean_token_accuracy": 0.8356277287006378, |
| "num_tokens": 27418078.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.4466124544541041, |
| "epoch": 0.0864, |
| "grad_norm": 1.078125, |
| "learning_rate": 1e-06, |
| "loss": 0.4647, |
| "mean_token_accuracy": 0.8362693071365357, |
| "num_tokens": 30842206.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.44751456181208293, |
| "epoch": 0.096, |
| "grad_norm": 0.953125, |
| "learning_rate": 1e-06, |
| "loss": 0.465, |
| "mean_token_accuracy": 0.8364668329556783, |
| "num_tokens": 34270915.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.44619213143984476, |
| "epoch": 0.1056, |
| "grad_norm": 0.96875, |
| "learning_rate": 1e-06, |
| "loss": 0.462, |
| "mean_token_accuracy": 0.8371777753035228, |
| "num_tokens": 37699757.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.4475706567366918, |
| "epoch": 0.1152, |
| "grad_norm": 1.0, |
| "learning_rate": 1e-06, |
| "loss": 0.4618, |
| "mean_token_accuracy": 0.8366606632868449, |
| "num_tokens": 41127680.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.44157906572024025, |
| "epoch": 0.1248, |
| "grad_norm": 0.953125, |
| "learning_rate": 1e-06, |
| "loss": 0.4539, |
| "mean_token_accuracy": 0.8387815574804942, |
| "num_tokens": 44550205.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.44636616806189217, |
| "epoch": 0.1344, |
| "grad_norm": 0.9375, |
| "learning_rate": 1e-06, |
| "loss": 0.4597, |
| "mean_token_accuracy": 0.8369020839532216, |
| "num_tokens": 47978530.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.45083456734816235, |
| "epoch": 0.144, |
| "grad_norm": 0.91015625, |
| "learning_rate": 1e-06, |
| "loss": 0.4615, |
| "mean_token_accuracy": 0.8364426136016846, |
| "num_tokens": 51415497.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.4423963377873103, |
| "epoch": 0.1536, |
| "grad_norm": 0.81640625, |
| "learning_rate": 1e-06, |
| "loss": 0.4531, |
| "mean_token_accuracy": 0.8387805402278901, |
| "num_tokens": 54843112.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.44047041336695353, |
| "epoch": 0.1632, |
| "grad_norm": 0.86328125, |
| "learning_rate": 1e-06, |
| "loss": 0.4509, |
| "mean_token_accuracy": 0.8391756375630697, |
| "num_tokens": 58269937.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.44535795946915946, |
| "epoch": 0.1728, |
| "grad_norm": 0.84765625, |
| "learning_rate": 1e-06, |
| "loss": 0.4549, |
| "mean_token_accuracy": 0.8376253386338551, |
| "num_tokens": 61698122.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.4441406190395355, |
| "epoch": 0.1824, |
| "grad_norm": 0.921875, |
| "learning_rate": 1e-06, |
| "loss": 0.4523, |
| "mean_token_accuracy": 0.8387903730074565, |
| "num_tokens": 65129853.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.4387974033753077, |
| "epoch": 0.192, |
| "grad_norm": 0.8046875, |
| "learning_rate": 1e-06, |
| "loss": 0.4475, |
| "mean_token_accuracy": 0.8403141776720683, |
| "num_tokens": 68554676.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.43539145588874817, |
| "epoch": 0.2016, |
| "grad_norm": 0.9921875, |
| "learning_rate": 1e-06, |
| "loss": 0.4451, |
| "mean_token_accuracy": 0.8406339287757874, |
| "num_tokens": 71978060.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.4371789425611496, |
| "epoch": 0.2112, |
| "grad_norm": 0.85546875, |
| "learning_rate": 1e-06, |
| "loss": 0.4457, |
| "mean_token_accuracy": 0.8400953491528829, |
| "num_tokens": 75401498.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.4436704327662786, |
| "epoch": 0.2208, |
| "grad_norm": 1.0234375, |
| "learning_rate": 1e-06, |
| "loss": 0.4512, |
| "mean_token_accuracy": 0.8383757730325063, |
| "num_tokens": 78829143.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.43721583088239035, |
| "epoch": 0.2304, |
| "grad_norm": 0.7578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4437, |
| "mean_token_accuracy": 0.8410045862197876, |
| "num_tokens": 82255415.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.43779849211374916, |
| "epoch": 0.24, |
| "grad_norm": 0.7890625, |
| "learning_rate": 1e-06, |
| "loss": 0.4449, |
| "mean_token_accuracy": 0.840403014421463, |
| "num_tokens": 85678092.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.4423576871554057, |
| "epoch": 0.2496, |
| "grad_norm": 0.7578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4496, |
| "mean_token_accuracy": 0.8392611801624298, |
| "num_tokens": 89108181.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.44207868178685505, |
| "epoch": 0.2592, |
| "grad_norm": 0.8359375, |
| "learning_rate": 1e-06, |
| "loss": 0.449, |
| "mean_token_accuracy": 0.8386734426021576, |
| "num_tokens": 92534098.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.43932537039120995, |
| "epoch": 0.2688, |
| "grad_norm": 0.76171875, |
| "learning_rate": 1e-06, |
| "loss": 0.4453, |
| "mean_token_accuracy": 0.8403779149055481, |
| "num_tokens": 95965587.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.44096320470174155, |
| "epoch": 0.2784, |
| "grad_norm": 0.8203125, |
| "learning_rate": 1e-06, |
| "loss": 0.447, |
| "mean_token_accuracy": 0.8391348044077556, |
| "num_tokens": 99394676.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.4383016347885132, |
| "epoch": 0.288, |
| "grad_norm": 0.70703125, |
| "learning_rate": 1e-06, |
| "loss": 0.4447, |
| "mean_token_accuracy": 0.840146021048228, |
| "num_tokens": 102821016.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.4389273832241694, |
| "epoch": 0.2976, |
| "grad_norm": 0.74609375, |
| "learning_rate": 1e-06, |
| "loss": 0.4452, |
| "mean_token_accuracy": 0.8401629229386648, |
| "num_tokens": 106250675.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.43793109953403475, |
| "epoch": 0.3072, |
| "grad_norm": 1.21875, |
| "learning_rate": 1e-06, |
| "loss": 0.4423, |
| "mean_token_accuracy": 0.8408861041069031, |
| "num_tokens": 109676233.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.4382920225461324, |
| "epoch": 0.3168, |
| "grad_norm": 0.72265625, |
| "learning_rate": 1e-06, |
| "loss": 0.4438, |
| "mean_token_accuracy": 0.840533846616745, |
| "num_tokens": 113104836.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.4332722157239914, |
| "epoch": 0.3264, |
| "grad_norm": 0.67578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4384, |
| "mean_token_accuracy": 0.8416322549184163, |
| "num_tokens": 116528992.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.43754682640234627, |
| "epoch": 0.336, |
| "grad_norm": 0.82421875, |
| "learning_rate": 1e-06, |
| "loss": 0.443, |
| "mean_token_accuracy": 0.8403245389461518, |
| "num_tokens": 119955123.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.42634722888469695, |
| "epoch": 0.3456, |
| "grad_norm": 0.76171875, |
| "learning_rate": 1e-06, |
| "loss": 0.4304, |
| "mean_token_accuracy": 0.844380776087443, |
| "num_tokens": 123374023.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.43683901329835256, |
| "epoch": 0.3552, |
| "grad_norm": 0.6875, |
| "learning_rate": 1e-06, |
| "loss": 0.4426, |
| "mean_token_accuracy": 0.8407382468382517, |
| "num_tokens": 126801597.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.4341103653113047, |
| "epoch": 0.3648, |
| "grad_norm": 0.95703125, |
| "learning_rate": 1e-06, |
| "loss": 0.4394, |
| "mean_token_accuracy": 0.8416337351004283, |
| "num_tokens": 130226608.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.43337511718273164, |
| "epoch": 0.3744, |
| "grad_norm": 0.76953125, |
| "learning_rate": 1e-06, |
| "loss": 0.4371, |
| "mean_token_accuracy": 0.8418285946051279, |
| "num_tokens": 133650147.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.43345692853132883, |
| "epoch": 0.384, |
| "grad_norm": 0.75, |
| "learning_rate": 1e-06, |
| "loss": 0.4371, |
| "mean_token_accuracy": 0.8420754154523213, |
| "num_tokens": 137072559.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.43710677921772, |
| "epoch": 0.3936, |
| "grad_norm": 0.734375, |
| "learning_rate": 1e-06, |
| "loss": 0.4418, |
| "mean_token_accuracy": 0.8403918604056041, |
| "num_tokens": 140502777.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.4345085640748342, |
| "epoch": 0.4032, |
| "grad_norm": 0.88671875, |
| "learning_rate": 1e-06, |
| "loss": 0.4382, |
| "mean_token_accuracy": 0.8418921589851379, |
| "num_tokens": 143932092.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.43460349341233573, |
| "epoch": 0.4128, |
| "grad_norm": 0.66796875, |
| "learning_rate": 1e-06, |
| "loss": 0.4391, |
| "mean_token_accuracy": 0.8413500209649404, |
| "num_tokens": 147358021.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.4344378610452016, |
| "epoch": 0.4224, |
| "grad_norm": 0.765625, |
| "learning_rate": 1e-06, |
| "loss": 0.4384, |
| "mean_token_accuracy": 0.8416643917560578, |
| "num_tokens": 150785208.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.43424378136793773, |
| "epoch": 0.432, |
| "grad_norm": 0.75390625, |
| "learning_rate": 1e-06, |
| "loss": 0.4378, |
| "mean_token_accuracy": 0.8417747735977172, |
| "num_tokens": 154214667.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.43412678241729735, |
| "epoch": 0.4416, |
| "grad_norm": 0.6484375, |
| "learning_rate": 1e-06, |
| "loss": 0.439, |
| "mean_token_accuracy": 0.8415433506170908, |
| "num_tokens": 157644805.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.4340047796567281, |
| "epoch": 0.4512, |
| "grad_norm": 0.6640625, |
| "learning_rate": 1e-06, |
| "loss": 0.4372, |
| "mean_token_accuracy": 0.8419170657793681, |
| "num_tokens": 161074326.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.4271635631720225, |
| "epoch": 0.4608, |
| "grad_norm": 0.65625, |
| "learning_rate": 1e-06, |
| "loss": 0.4295, |
| "mean_token_accuracy": 0.8433916787306468, |
| "num_tokens": 164493009.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.4347446064154307, |
| "epoch": 0.4704, |
| "grad_norm": 0.7109375, |
| "learning_rate": 1e-06, |
| "loss": 0.4385, |
| "mean_token_accuracy": 0.8410797854264577, |
| "num_tokens": 167922637.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.43026507596174873, |
| "epoch": 0.48, |
| "grad_norm": 0.6640625, |
| "learning_rate": 1e-06, |
| "loss": 0.433, |
| "mean_token_accuracy": 0.8427020668983459, |
| "num_tokens": 171349238.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.43025335570176443, |
| "epoch": 0.4896, |
| "grad_norm": 0.67578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4332, |
| "mean_token_accuracy": 0.8427554865678152, |
| "num_tokens": 174774665.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.43068666458129884, |
| "epoch": 0.4992, |
| "grad_norm": 0.67578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4343, |
| "mean_token_accuracy": 0.8422266582647959, |
| "num_tokens": 178199588.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.4314758092164993, |
| "epoch": 0.5088, |
| "grad_norm": 0.69140625, |
| "learning_rate": 1e-06, |
| "loss": 0.4341, |
| "mean_token_accuracy": 0.8423931996027628, |
| "num_tokens": 181622373.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.43214026689529417, |
| "epoch": 0.5184, |
| "grad_norm": 0.62890625, |
| "learning_rate": 1e-06, |
| "loss": 0.4352, |
| "mean_token_accuracy": 0.8417826076348622, |
| "num_tokens": 185046141.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.42929191191991173, |
| "epoch": 0.528, |
| "grad_norm": 0.6484375, |
| "learning_rate": 1e-06, |
| "loss": 0.4315, |
| "mean_token_accuracy": 0.8429112037022909, |
| "num_tokens": 188471598.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.43347863058249153, |
| "epoch": 0.5376, |
| "grad_norm": 0.6796875, |
| "learning_rate": 1e-06, |
| "loss": 0.4362, |
| "mean_token_accuracy": 0.8421526908874511, |
| "num_tokens": 191901663.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.4340634206930796, |
| "epoch": 0.5472, |
| "grad_norm": 0.703125, |
| "learning_rate": 1e-06, |
| "loss": 0.4385, |
| "mean_token_accuracy": 0.8407556653022766, |
| "num_tokens": 195330705.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.4317493091026942, |
| "epoch": 0.5568, |
| "grad_norm": 0.640625, |
| "learning_rate": 1e-06, |
| "loss": 0.4341, |
| "mean_token_accuracy": 0.8426395455996195, |
| "num_tokens": 198759569.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.4264296998580297, |
| "epoch": 0.5664, |
| "grad_norm": 0.79296875, |
| "learning_rate": 1e-06, |
| "loss": 0.4288, |
| "mean_token_accuracy": 0.843881368637085, |
| "num_tokens": 202180759.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.42934685150782265, |
| "epoch": 0.576, |
| "grad_norm": 0.66796875, |
| "learning_rate": 1e-06, |
| "loss": 0.4319, |
| "mean_token_accuracy": 0.8431523183981577, |
| "num_tokens": 205609433.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.43238858282566073, |
| "epoch": 0.5856, |
| "grad_norm": 0.69921875, |
| "learning_rate": 1e-06, |
| "loss": 0.4351, |
| "mean_token_accuracy": 0.8418097396691641, |
| "num_tokens": 209040734.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.4318026860555013, |
| "epoch": 0.5952, |
| "grad_norm": 0.6328125, |
| "learning_rate": 1e-06, |
| "loss": 0.4355, |
| "mean_token_accuracy": 0.8424915373325348, |
| "num_tokens": 212473401.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.4235608865817388, |
| "epoch": 0.6048, |
| "grad_norm": 0.6015625, |
| "learning_rate": 1e-06, |
| "loss": 0.4256, |
| "mean_token_accuracy": 0.8451377809047699, |
| "num_tokens": 215896965.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.42819432020187376, |
| "epoch": 0.6144, |
| "grad_norm": 1.1484375, |
| "learning_rate": 1e-06, |
| "loss": 0.4307, |
| "mean_token_accuracy": 0.8432986001173656, |
| "num_tokens": 219323070.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.43294126689434054, |
| "epoch": 0.624, |
| "grad_norm": 0.70703125, |
| "learning_rate": 1e-06, |
| "loss": 0.4357, |
| "mean_token_accuracy": 0.8416835029919942, |
| "num_tokens": 222753922.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.42949473758538564, |
| "epoch": 0.6336, |
| "grad_norm": 0.734375, |
| "learning_rate": 1e-06, |
| "loss": 0.4329, |
| "mean_token_accuracy": 0.8425247291723887, |
| "num_tokens": 226181564.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.431626628835996, |
| "epoch": 0.6432, |
| "grad_norm": 0.9140625, |
| "learning_rate": 1e-06, |
| "loss": 0.4342, |
| "mean_token_accuracy": 0.8420288483301799, |
| "num_tokens": 229609454.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.42529774804910025, |
| "epoch": 0.6528, |
| "grad_norm": 0.7109375, |
| "learning_rate": 1e-06, |
| "loss": 0.4283, |
| "mean_token_accuracy": 0.8438542902469635, |
| "num_tokens": 233030434.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.4295430819193522, |
| "epoch": 0.6624, |
| "grad_norm": 0.7109375, |
| "learning_rate": 1e-06, |
| "loss": 0.4319, |
| "mean_token_accuracy": 0.8431335310141246, |
| "num_tokens": 236458053.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.4359436571598053, |
| "epoch": 0.672, |
| "grad_norm": 0.875, |
| "learning_rate": 1e-06, |
| "loss": 0.4387, |
| "mean_token_accuracy": 0.8408014853795369, |
| "num_tokens": 239892329.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.43046695590019224, |
| "epoch": 0.6816, |
| "grad_norm": 0.83203125, |
| "learning_rate": 1e-06, |
| "loss": 0.4329, |
| "mean_token_accuracy": 0.8423032621542613, |
| "num_tokens": 243321186.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.427196944753329, |
| "epoch": 0.6912, |
| "grad_norm": 0.578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4296, |
| "mean_token_accuracy": 0.8436582644780477, |
| "num_tokens": 246748277.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.4301902174949646, |
| "epoch": 0.7008, |
| "grad_norm": 0.6484375, |
| "learning_rate": 1e-06, |
| "loss": 0.4319, |
| "mean_token_accuracy": 0.8430530607700348, |
| "num_tokens": 250176097.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.42852813402811685, |
| "epoch": 0.7104, |
| "grad_norm": 0.81640625, |
| "learning_rate": 1e-06, |
| "loss": 0.4308, |
| "mean_token_accuracy": 0.8430961946646373, |
| "num_tokens": 253603786.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.4267232229312261, |
| "epoch": 0.72, |
| "grad_norm": 0.66015625, |
| "learning_rate": 1e-06, |
| "loss": 0.4294, |
| "mean_token_accuracy": 0.8436786532402039, |
| "num_tokens": 257030085.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.42847318251927696, |
| "epoch": 0.7296, |
| "grad_norm": 0.9453125, |
| "learning_rate": 1e-06, |
| "loss": 0.4313, |
| "mean_token_accuracy": 0.8432875255743663, |
| "num_tokens": 260459662.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.42785159647464754, |
| "epoch": 0.7392, |
| "grad_norm": 0.65234375, |
| "learning_rate": 1e-06, |
| "loss": 0.4296, |
| "mean_token_accuracy": 0.8437132080396016, |
| "num_tokens": 263886799.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.42436840136845905, |
| "epoch": 0.7488, |
| "grad_norm": 0.7734375, |
| "learning_rate": 1e-06, |
| "loss": 0.4271, |
| "mean_token_accuracy": 0.8438882827758789, |
| "num_tokens": 267311788.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.42350135842959086, |
| "epoch": 0.7584, |
| "grad_norm": 0.71484375, |
| "learning_rate": 1e-06, |
| "loss": 0.4244, |
| "mean_token_accuracy": 0.8450363477071127, |
| "num_tokens": 270733591.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.42643423279126486, |
| "epoch": 0.768, |
| "grad_norm": 0.73828125, |
| "learning_rate": 1e-06, |
| "loss": 0.4289, |
| "mean_token_accuracy": 0.8439076920350392, |
| "num_tokens": 274158074.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.4293264577786128, |
| "epoch": 0.7776, |
| "grad_norm": 0.76171875, |
| "learning_rate": 1e-06, |
| "loss": 0.4324, |
| "mean_token_accuracy": 0.8420809169610342, |
| "num_tokens": 277581909.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.42917039692401887, |
| "epoch": 0.7872, |
| "grad_norm": 0.74609375, |
| "learning_rate": 1e-06, |
| "loss": 0.4308, |
| "mean_token_accuracy": 0.842545215288798, |
| "num_tokens": 281007702.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.4337611397107442, |
| "epoch": 0.7968, |
| "grad_norm": 0.71484375, |
| "learning_rate": 1e-06, |
| "loss": 0.4356, |
| "mean_token_accuracy": 0.8417014559110005, |
| "num_tokens": 284442105.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.42585750023523966, |
| "epoch": 0.8064, |
| "grad_norm": 0.60546875, |
| "learning_rate": 1e-06, |
| "loss": 0.4281, |
| "mean_token_accuracy": 0.8437936822573344, |
| "num_tokens": 287868793.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.4264136056105296, |
| "epoch": 0.816, |
| "grad_norm": 0.9296875, |
| "learning_rate": 1e-06, |
| "loss": 0.4291, |
| "mean_token_accuracy": 0.8439127763112386, |
| "num_tokens": 291295752.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.4276336113611857, |
| "epoch": 0.8256, |
| "grad_norm": 0.69140625, |
| "learning_rate": 1e-06, |
| "loss": 0.4294, |
| "mean_token_accuracy": 0.8433744112650553, |
| "num_tokens": 294724526.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.4295493682225545, |
| "epoch": 0.8352, |
| "grad_norm": 0.67578125, |
| "learning_rate": 1e-06, |
| "loss": 0.4314, |
| "mean_token_accuracy": 0.8426620582739512, |
| "num_tokens": 298153923.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.42792819142341615, |
| "epoch": 0.8448, |
| "grad_norm": 0.76953125, |
| "learning_rate": 1e-06, |
| "loss": 0.4304, |
| "mean_token_accuracy": 0.8432036856810252, |
| "num_tokens": 301584253.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.42749512096246084, |
| "epoch": 0.8544, |
| "grad_norm": 0.77734375, |
| "learning_rate": 1e-06, |
| "loss": 0.4299, |
| "mean_token_accuracy": 0.8432926038901011, |
| "num_tokens": 305013666.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.4297857642173767, |
| "epoch": 0.864, |
| "grad_norm": 0.83984375, |
| "learning_rate": 1e-06, |
| "loss": 0.4318, |
| "mean_token_accuracy": 0.8426412324110667, |
| "num_tokens": 308440989.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.42787257631619774, |
| "epoch": 0.8736, |
| "grad_norm": 0.66015625, |
| "learning_rate": 1e-06, |
| "loss": 0.4303, |
| "mean_token_accuracy": 0.8433160742123922, |
| "num_tokens": 311870076.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 0.42855414350827536, |
| "epoch": 0.8832, |
| "grad_norm": 0.71875, |
| "learning_rate": 1e-06, |
| "loss": 0.4303, |
| "mean_token_accuracy": 0.8432195166746775, |
| "num_tokens": 315296851.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 0.42333943645159405, |
| "epoch": 0.8928, |
| "grad_norm": 0.625, |
| "learning_rate": 1e-06, |
| "loss": 0.4242, |
| "mean_token_accuracy": 0.8448341071605683, |
| "num_tokens": 318720357.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 0.4254674275716146, |
| "epoch": 0.9024, |
| "grad_norm": 0.69140625, |
| "learning_rate": 1e-06, |
| "loss": 0.4272, |
| "mean_token_accuracy": 0.844523819287618, |
| "num_tokens": 322150685.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 0.4280929406483968, |
| "epoch": 0.912, |
| "grad_norm": 0.609375, |
| "learning_rate": 1e-06, |
| "loss": 0.4305, |
| "mean_token_accuracy": 0.8432438095410665, |
| "num_tokens": 325578800.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.4216255853573481, |
| "epoch": 0.9216, |
| "grad_norm": 0.76171875, |
| "learning_rate": 1e-06, |
| "loss": 0.4233, |
| "mean_token_accuracy": 0.8448065340518951, |
| "num_tokens": 328999744.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 0.42576794425646464, |
| "epoch": 0.9312, |
| "grad_norm": 0.78515625, |
| "learning_rate": 1e-06, |
| "loss": 0.4274, |
| "mean_token_accuracy": 0.8436802566051483, |
| "num_tokens": 332424272.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 0.41938706636428835, |
| "epoch": 0.9408, |
| "grad_norm": 0.60546875, |
| "learning_rate": 1e-06, |
| "loss": 0.4206, |
| "mean_token_accuracy": 0.8458850880463918, |
| "num_tokens": 335842047.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 0.4206093430519104, |
| "epoch": 0.9504, |
| "grad_norm": 0.78515625, |
| "learning_rate": 1e-06, |
| "loss": 0.4237, |
| "mean_token_accuracy": 0.8452507853507996, |
| "num_tokens": 339266824.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 0.42829200327396394, |
| "epoch": 0.96, |
| "grad_norm": 0.6875, |
| "learning_rate": 1e-06, |
| "loss": 0.4304, |
| "mean_token_accuracy": 0.842687439918518, |
| "num_tokens": 342692717.0, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1042, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.762403376047587e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
