| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.780281533411228, |
| "eval_steps": 100, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.7622424783185124, |
| "epoch": 0.004451121126133645, |
| "grad_norm": 1888.0, |
| "learning_rate": 1.8e-07, |
| "loss": 36.8185, |
| "mean_token_accuracy": 0.6663544788956642, |
| "num_tokens": 63133.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.8160548411309719, |
| "epoch": 0.00890224225226729, |
| "grad_norm": 1728.0, |
| "learning_rate": 3.8e-07, |
| "loss": 36.6381, |
| "mean_token_accuracy": 0.649208546616137, |
| "num_tokens": 128968.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.8332255953922868, |
| "epoch": 0.013353363378400934, |
| "grad_norm": 948.0, |
| "learning_rate": 5.800000000000001e-07, |
| "loss": 34.7797, |
| "mean_token_accuracy": 0.6578839531168341, |
| "num_tokens": 193314.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.9456521481275558, |
| "epoch": 0.01780448450453458, |
| "grad_norm": 716.0, |
| "learning_rate": 7.8e-07, |
| "loss": 34.1076, |
| "mean_token_accuracy": 0.6613732609897852, |
| "num_tokens": 257189.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.9749895730987191, |
| "epoch": 0.022255605630668224, |
| "grad_norm": 660.0, |
| "learning_rate": 9.800000000000001e-07, |
| "loss": 29.937, |
| "mean_token_accuracy": 0.6729008939117194, |
| "num_tokens": 324224.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.0305172327905894, |
| "epoch": 0.026706726756801868, |
| "grad_norm": 492.0, |
| "learning_rate": 1.1800000000000001e-06, |
| "loss": 28.3561, |
| "mean_token_accuracy": 0.680633837915957, |
| "num_tokens": 394654.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.0123192116618156, |
| "epoch": 0.031157847882935515, |
| "grad_norm": 404.0, |
| "learning_rate": 1.3800000000000001e-06, |
| "loss": 26.0449, |
| "mean_token_accuracy": 0.6903208963572979, |
| "num_tokens": 461658.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.024911842495203, |
| "epoch": 0.03560896900906916, |
| "grad_norm": 250.0, |
| "learning_rate": 1.5800000000000001e-06, |
| "loss": 23.6986, |
| "mean_token_accuracy": 0.6996766375377774, |
| "num_tokens": 528285.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.0939506959170102, |
| "epoch": 0.04006009013520281, |
| "grad_norm": 227.0, |
| "learning_rate": 1.7800000000000001e-06, |
| "loss": 23.2949, |
| "mean_token_accuracy": 0.6969541085883975, |
| "num_tokens": 595336.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.0676697574555873, |
| "epoch": 0.04451121126133645, |
| "grad_norm": 278.0, |
| "learning_rate": 1.98e-06, |
| "loss": 21.5533, |
| "mean_token_accuracy": 0.7063678905367852, |
| "num_tokens": 663126.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04451121126133645, |
| "eval_biology_entropy": 1.5063953498601914, |
| "eval_biology_loss": 1.9373619556427002, |
| "eval_biology_mean_token_accuracy": 0.6030384682416916, |
| "eval_biology_num_tokens": 663126.0, |
| "eval_biology_runtime": 37.2317, |
| "eval_biology_samples_per_second": 13.429, |
| "eval_biology_steps_per_second": 13.429, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04451121126133645, |
| "eval_chemistry_entropy": 1.0538504299521447, |
| "eval_chemistry_loss": 1.2949438095092773, |
| "eval_chemistry_mean_token_accuracy": 0.7114702309370041, |
| "eval_chemistry_num_tokens": 663126.0, |
| "eval_chemistry_runtime": 41.1049, |
| "eval_chemistry_samples_per_second": 12.164, |
| "eval_chemistry_steps_per_second": 12.164, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04451121126133645, |
| "eval_math_entropy": 0.8524410739541054, |
| "eval_math_loss": 1.2029013633728027, |
| "eval_math_mean_token_accuracy": 0.7322385207414627, |
| "eval_math_num_tokens": 663126.0, |
| "eval_math_runtime": 41.5152, |
| "eval_math_samples_per_second": 12.044, |
| "eval_math_steps_per_second": 12.044, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04451121126133645, |
| "eval_physics_entropy": 0.9442882173061371, |
| "eval_physics_loss": 1.1572656631469727, |
| "eval_physics_mean_token_accuracy": 0.7343679416179657, |
| "eval_physics_num_tokens": 663126.0, |
| "eval_physics_runtime": 45.8024, |
| "eval_physics_samples_per_second": 10.916, |
| "eval_physics_steps_per_second": 10.916, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0567705381661654, |
| "epoch": 0.048962332387470095, |
| "grad_norm": 202.0, |
| "learning_rate": 2.1800000000000003e-06, |
| "loss": 20.0858, |
| "mean_token_accuracy": 0.7180810730904341, |
| "num_tokens": 731060.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.0101547280326486, |
| "epoch": 0.053413453513603736, |
| "grad_norm": 202.0, |
| "learning_rate": 2.38e-06, |
| "loss": 18.8763, |
| "mean_token_accuracy": 0.7310481067746878, |
| "num_tokens": 801635.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 1.0049639470875262, |
| "epoch": 0.05786457463973738, |
| "grad_norm": 154.0, |
| "learning_rate": 2.5800000000000003e-06, |
| "loss": 19.1729, |
| "mean_token_accuracy": 0.7293503576889634, |
| "num_tokens": 867260.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.0176106113940477, |
| "epoch": 0.06231569576587103, |
| "grad_norm": 144.0, |
| "learning_rate": 2.7800000000000005e-06, |
| "loss": 18.97, |
| "mean_token_accuracy": 0.7298020845279097, |
| "num_tokens": 931344.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.0698495015501976, |
| "epoch": 0.06676681689200467, |
| "grad_norm": 169.0, |
| "learning_rate": 2.9800000000000003e-06, |
| "loss": 17.4943, |
| "mean_token_accuracy": 0.7370716020464897, |
| "num_tokens": 993586.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.0634983357042074, |
| "epoch": 0.07121793801813832, |
| "grad_norm": 123.0, |
| "learning_rate": 3.1800000000000005e-06, |
| "loss": 16.9373, |
| "mean_token_accuracy": 0.7367568526417017, |
| "num_tokens": 1060812.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 1.0108168195933103, |
| "epoch": 0.07566905914427197, |
| "grad_norm": 125.0, |
| "learning_rate": 3.3800000000000007e-06, |
| "loss": 15.569, |
| "mean_token_accuracy": 0.7519758876413107, |
| "num_tokens": 1131832.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.9829567475244403, |
| "epoch": 0.08012018027040561, |
| "grad_norm": 99.0, |
| "learning_rate": 3.58e-06, |
| "loss": 15.2082, |
| "mean_token_accuracy": 0.7475447814911604, |
| "num_tokens": 1200650.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.9538513226434588, |
| "epoch": 0.08457130139653925, |
| "grad_norm": 119.0, |
| "learning_rate": 3.7800000000000002e-06, |
| "loss": 15.0014, |
| "mean_token_accuracy": 0.7515964422374963, |
| "num_tokens": 1265107.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.9125228714197874, |
| "epoch": 0.0890224225226729, |
| "grad_norm": 117.0, |
| "learning_rate": 3.980000000000001e-06, |
| "loss": 14.4833, |
| "mean_token_accuracy": 0.7538308618590236, |
| "num_tokens": 1327380.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0890224225226729, |
| "eval_biology_entropy": 1.280277446448803, |
| "eval_biology_loss": 1.453066349029541, |
| "eval_biology_mean_token_accuracy": 0.6518876985907555, |
| "eval_biology_num_tokens": 1327380.0, |
| "eval_biology_runtime": 36.821, |
| "eval_biology_samples_per_second": 13.579, |
| "eval_biology_steps_per_second": 13.579, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0890224225226729, |
| "eval_chemistry_entropy": 0.8954760466217995, |
| "eval_chemistry_loss": 0.9106767177581787, |
| "eval_chemistry_mean_token_accuracy": 0.7551076735854149, |
| "eval_chemistry_num_tokens": 1327380.0, |
| "eval_chemistry_runtime": 40.4689, |
| "eval_chemistry_samples_per_second": 12.355, |
| "eval_chemistry_steps_per_second": 12.355, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0890224225226729, |
| "eval_math_entropy": 0.7658050524294376, |
| "eval_math_loss": 0.9040815234184265, |
| "eval_math_mean_token_accuracy": 0.7642563463449478, |
| "eval_math_num_tokens": 1327380.0, |
| "eval_math_runtime": 41.4556, |
| "eval_math_samples_per_second": 12.061, |
| "eval_math_steps_per_second": 12.061, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0890224225226729, |
| "eval_physics_entropy": 0.8174435417056084, |
| "eval_physics_loss": 0.8484614491462708, |
| "eval_physics_mean_token_accuracy": 0.7708570960760116, |
| "eval_physics_num_tokens": 1327380.0, |
| "eval_physics_runtime": 45.875, |
| "eval_physics_samples_per_second": 10.899, |
| "eval_physics_steps_per_second": 10.899, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.9408239619806409, |
| "epoch": 0.09347354364880654, |
| "grad_norm": 126.5, |
| "learning_rate": 4.18e-06, |
| "loss": 15.2387, |
| "mean_token_accuracy": 0.7457781180739402, |
| "num_tokens": 1393379.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.8950148992240429, |
| "epoch": 0.09792466477494019, |
| "grad_norm": 95.0, |
| "learning_rate": 4.38e-06, |
| "loss": 14.2337, |
| "mean_token_accuracy": 0.7587446294724941, |
| "num_tokens": 1460130.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.859116705879569, |
| "epoch": 0.10237578590107384, |
| "grad_norm": 94.0, |
| "learning_rate": 4.58e-06, |
| "loss": 13.7082, |
| "mean_token_accuracy": 0.76347241923213, |
| "num_tokens": 1529183.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.8980951353907585, |
| "epoch": 0.10682690702720747, |
| "grad_norm": 118.5, |
| "learning_rate": 4.78e-06, |
| "loss": 14.5897, |
| "mean_token_accuracy": 0.7553087200969457, |
| "num_tokens": 1597405.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.9019628280773759, |
| "epoch": 0.11127802815334112, |
| "grad_norm": 98.5, |
| "learning_rate": 4.980000000000001e-06, |
| "loss": 14.5049, |
| "mean_token_accuracy": 0.7539074700325727, |
| "num_tokens": 1661767.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.9095736019313335, |
| "epoch": 0.11572914927947477, |
| "grad_norm": 80.0, |
| "learning_rate": 5.18e-06, |
| "loss": 14.553, |
| "mean_token_accuracy": 0.7567780796438456, |
| "num_tokens": 1728207.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.855735239200294, |
| "epoch": 0.12018027040560841, |
| "grad_norm": 99.0, |
| "learning_rate": 5.380000000000001e-06, |
| "loss": 13.731, |
| "mean_token_accuracy": 0.7652106903493404, |
| "num_tokens": 1796055.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.830021676234901, |
| "epoch": 0.12463139153174206, |
| "grad_norm": 97.5, |
| "learning_rate": 5.580000000000001e-06, |
| "loss": 13.2554, |
| "mean_token_accuracy": 0.7721017152070999, |
| "num_tokens": 1859684.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.8921441739425063, |
| "epoch": 0.1290825126578757, |
| "grad_norm": 106.5, |
| "learning_rate": 5.78e-06, |
| "loss": 14.4012, |
| "mean_token_accuracy": 0.7561684042215348, |
| "num_tokens": 1921704.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.8731818461790681, |
| "epoch": 0.13353363378400934, |
| "grad_norm": 87.5, |
| "learning_rate": 5.98e-06, |
| "loss": 13.9502, |
| "mean_token_accuracy": 0.7628704030066729, |
| "num_tokens": 1985766.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13353363378400934, |
| "eval_biology_entropy": 1.2637426958680154, |
| "eval_biology_loss": 1.3796980381011963, |
| "eval_biology_mean_token_accuracy": 0.6648430502414704, |
| "eval_biology_num_tokens": 1985766.0, |
| "eval_biology_runtime": 37.0397, |
| "eval_biology_samples_per_second": 13.499, |
| "eval_biology_steps_per_second": 13.499, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13353363378400934, |
| "eval_chemistry_entropy": 0.8489444836974144, |
| "eval_chemistry_loss": 0.8385273814201355, |
| "eval_chemistry_mean_token_accuracy": 0.7699487572312355, |
| "eval_chemistry_num_tokens": 1985766.0, |
| "eval_chemistry_runtime": 40.8665, |
| "eval_chemistry_samples_per_second": 12.235, |
| "eval_chemistry_steps_per_second": 12.235, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13353363378400934, |
| "eval_math_entropy": 0.7357360773980618, |
| "eval_math_loss": 0.8767910599708557, |
| "eval_math_mean_token_accuracy": 0.7708948514461518, |
| "eval_math_num_tokens": 1985766.0, |
| "eval_math_runtime": 41.8192, |
| "eval_math_samples_per_second": 11.956, |
| "eval_math_steps_per_second": 11.956, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13353363378400934, |
| "eval_physics_entropy": 0.7905060887336731, |
| "eval_physics_loss": 0.7890318632125854, |
| "eval_physics_mean_token_accuracy": 0.7825853993296623, |
| "eval_physics_num_tokens": 1985766.0, |
| "eval_physics_runtime": 46.1418, |
| "eval_physics_samples_per_second": 10.836, |
| "eval_physics_steps_per_second": 10.836, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.8452363438904286, |
| "epoch": 0.137984754910143, |
| "grad_norm": 96.0, |
| "learning_rate": 6.18e-06, |
| "loss": 13.634, |
| "mean_token_accuracy": 0.7645608998835087, |
| "num_tokens": 2049041.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.8076417898759246, |
| "epoch": 0.14243587603627664, |
| "grad_norm": 80.5, |
| "learning_rate": 6.380000000000001e-06, |
| "loss": 12.8943, |
| "mean_token_accuracy": 0.7760006580501795, |
| "num_tokens": 2118068.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.8085115062072873, |
| "epoch": 0.14688699716241027, |
| "grad_norm": 106.5, |
| "learning_rate": 6.5800000000000005e-06, |
| "loss": 12.7928, |
| "mean_token_accuracy": 0.7790838234126568, |
| "num_tokens": 2186387.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.824213713593781, |
| "epoch": 0.15133811828854393, |
| "grad_norm": 82.5, |
| "learning_rate": 6.780000000000001e-06, |
| "loss": 13.389, |
| "mean_token_accuracy": 0.7689453203231096, |
| "num_tokens": 2252650.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.797634300775826, |
| "epoch": 0.15578923941467757, |
| "grad_norm": 85.5, |
| "learning_rate": 6.98e-06, |
| "loss": 12.8088, |
| "mean_token_accuracy": 0.7797435287386179, |
| "num_tokens": 2320358.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.7920836627483367, |
| "epoch": 0.16024036054081123, |
| "grad_norm": 88.0, |
| "learning_rate": 7.180000000000001e-06, |
| "loss": 12.6336, |
| "mean_token_accuracy": 0.7806293956935406, |
| "num_tokens": 2388824.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.7749077206477523, |
| "epoch": 0.16469148166694486, |
| "grad_norm": 80.5, |
| "learning_rate": 7.3800000000000005e-06, |
| "loss": 12.3995, |
| "mean_token_accuracy": 0.7864189695566892, |
| "num_tokens": 2456144.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.8578483302146196, |
| "epoch": 0.1691426027930785, |
| "grad_norm": 81.0, |
| "learning_rate": 7.58e-06, |
| "loss": 13.8496, |
| "mean_token_accuracy": 0.7662820883095265, |
| "num_tokens": 2515325.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.7971056224778295, |
| "epoch": 0.17359372391921216, |
| "grad_norm": 68.0, |
| "learning_rate": 7.78e-06, |
| "loss": 12.6922, |
| "mean_token_accuracy": 0.7778837148100137, |
| "num_tokens": 2580490.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.7984419580549001, |
| "epoch": 0.1780448450453458, |
| "grad_norm": 70.5, |
| "learning_rate": 7.980000000000002e-06, |
| "loss": 12.8255, |
| "mean_token_accuracy": 0.7773921977728605, |
| "num_tokens": 2644330.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1780448450453458, |
| "eval_biology_entropy": 1.2305693982243537, |
| "eval_biology_loss": 1.3490314483642578, |
| "eval_biology_mean_token_accuracy": 0.6716532117724419, |
| "eval_biology_num_tokens": 2644330.0, |
| "eval_biology_runtime": 36.6001, |
| "eval_biology_samples_per_second": 13.661, |
| "eval_biology_steps_per_second": 13.661, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1780448450453458, |
| "eval_chemistry_entropy": 0.7882854393720626, |
| "eval_chemistry_loss": 0.7991188764572144, |
| "eval_chemistry_mean_token_accuracy": 0.778610565006733, |
| "eval_chemistry_num_tokens": 2644330.0, |
| "eval_chemistry_runtime": 40.3843, |
| "eval_chemistry_samples_per_second": 12.381, |
| "eval_chemistry_steps_per_second": 12.381, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1780448450453458, |
| "eval_math_entropy": 0.6974474709928036, |
| "eval_math_loss": 0.8647986054420471, |
| "eval_math_mean_token_accuracy": 0.7742947788238526, |
| "eval_math_num_tokens": 2644330.0, |
| "eval_math_runtime": 41.8502, |
| "eval_math_samples_per_second": 11.947, |
| "eval_math_steps_per_second": 11.947, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1780448450453458, |
| "eval_physics_entropy": 0.740912606716156, |
| "eval_physics_loss": 0.7630434632301331, |
| "eval_physics_mean_token_accuracy": 0.7882855938673019, |
| "eval_physics_num_tokens": 2644330.0, |
| "eval_physics_runtime": 46.1492, |
| "eval_physics_samples_per_second": 10.834, |
| "eval_physics_steps_per_second": 10.834, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.7443430663086474, |
| "epoch": 0.18249596617147945, |
| "grad_norm": 72.5, |
| "learning_rate": 8.18e-06, |
| "loss": 11.7994, |
| "mean_token_accuracy": 0.7938185524195432, |
| "num_tokens": 2713234.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.7856309018097818, |
| "epoch": 0.18694708729761308, |
| "grad_norm": 78.0, |
| "learning_rate": 8.380000000000001e-06, |
| "loss": 12.9567, |
| "mean_token_accuracy": 0.7781453486531973, |
| "num_tokens": 2783261.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.799421458132565, |
| "epoch": 0.19139820842374672, |
| "grad_norm": 61.25, |
| "learning_rate": 8.580000000000001e-06, |
| "loss": 12.6392, |
| "mean_token_accuracy": 0.7806750666350126, |
| "num_tokens": 2850170.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.7786322007887065, |
| "epoch": 0.19584932954988038, |
| "grad_norm": 80.5, |
| "learning_rate": 8.78e-06, |
| "loss": 12.4988, |
| "mean_token_accuracy": 0.7827117882668972, |
| "num_tokens": 2913700.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.763565490860492, |
| "epoch": 0.200300450676014, |
| "grad_norm": 81.0, |
| "learning_rate": 8.98e-06, |
| "loss": 12.4779, |
| "mean_token_accuracy": 0.7831043265759945, |
| "num_tokens": 2981212.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.7708647299557925, |
| "epoch": 0.20475157180214767, |
| "grad_norm": 85.0, |
| "learning_rate": 9.180000000000002e-06, |
| "loss": 12.1503, |
| "mean_token_accuracy": 0.7912418570369482, |
| "num_tokens": 3048973.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.769937212113291, |
| "epoch": 0.2092026929282813, |
| "grad_norm": 62.0, |
| "learning_rate": 9.38e-06, |
| "loss": 12.6137, |
| "mean_token_accuracy": 0.7829986553639173, |
| "num_tokens": 3117033.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.7863288868218661, |
| "epoch": 0.21365381405441494, |
| "grad_norm": 74.5, |
| "learning_rate": 9.58e-06, |
| "loss": 12.3857, |
| "mean_token_accuracy": 0.7842021461576223, |
| "num_tokens": 3185255.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.7699232887476682, |
| "epoch": 0.2181049351805486, |
| "grad_norm": 74.5, |
| "learning_rate": 9.780000000000001e-06, |
| "loss": 12.4166, |
| "mean_token_accuracy": 0.7846909243613481, |
| "num_tokens": 3253121.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.7251296367496252, |
| "epoch": 0.22255605630668224, |
| "grad_norm": 75.0, |
| "learning_rate": 9.980000000000001e-06, |
| "loss": 11.4498, |
| "mean_token_accuracy": 0.7972834445536137, |
| "num_tokens": 3322823.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22255605630668224, |
| "eval_biology_entropy": 1.1898637573719024, |
| "eval_biology_loss": 1.338150978088379, |
| "eval_biology_mean_token_accuracy": 0.6746688461303711, |
| "eval_biology_num_tokens": 3322823.0, |
| "eval_biology_runtime": 37.4484, |
| "eval_biology_samples_per_second": 13.352, |
| "eval_biology_steps_per_second": 13.352, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22255605630668224, |
| "eval_chemistry_entropy": 0.7506220785379409, |
| "eval_chemistry_loss": 0.7758934497833252, |
| "eval_chemistry_mean_token_accuracy": 0.7828538768291473, |
| "eval_chemistry_num_tokens": 3322823.0, |
| "eval_chemistry_runtime": 40.7375, |
| "eval_chemistry_samples_per_second": 12.274, |
| "eval_chemistry_steps_per_second": 12.274, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22255605630668224, |
| "eval_math_entropy": 0.6889803909361363, |
| "eval_math_loss": 0.8622512817382812, |
| "eval_math_mean_token_accuracy": 0.7754237843751908, |
| "eval_math_num_tokens": 3322823.0, |
| "eval_math_runtime": 41.9238, |
| "eval_math_samples_per_second": 11.926, |
| "eval_math_steps_per_second": 11.926, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22255605630668224, |
| "eval_physics_entropy": 0.7242196025848389, |
| "eval_physics_loss": 0.7506964802742004, |
| "eval_physics_mean_token_accuracy": 0.7921671935915947, |
| "eval_physics_num_tokens": 3322823.0, |
| "eval_physics_runtime": 45.9692, |
| "eval_physics_samples_per_second": 10.877, |
| "eval_physics_steps_per_second": 10.877, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.7351194931194186, |
| "epoch": 0.2270071774328159, |
| "grad_norm": 75.0, |
| "learning_rate": 1.018e-05, |
| "loss": 11.9225, |
| "mean_token_accuracy": 0.7910898551344872, |
| "num_tokens": 3393393.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.8338562373071909, |
| "epoch": 0.23145829855894953, |
| "grad_norm": 79.0, |
| "learning_rate": 1.038e-05, |
| "loss": 13.1291, |
| "mean_token_accuracy": 0.774738060683012, |
| "num_tokens": 3454750.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.7108834735117853, |
| "epoch": 0.2359094196850832, |
| "grad_norm": 70.5, |
| "learning_rate": 1.0580000000000002e-05, |
| "loss": 11.7207, |
| "mean_token_accuracy": 0.7975892208516597, |
| "num_tokens": 3526914.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.8373067150823772, |
| "epoch": 0.24036054081121683, |
| "grad_norm": 72.0, |
| "learning_rate": 1.0780000000000002e-05, |
| "loss": 13.0512, |
| "mean_token_accuracy": 0.7754946660250426, |
| "num_tokens": 3589449.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.7569006633013486, |
| "epoch": 0.24481166193735046, |
| "grad_norm": 79.0, |
| "learning_rate": 1.0980000000000002e-05, |
| "loss": 12.267, |
| "mean_token_accuracy": 0.786787087097764, |
| "num_tokens": 3655092.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.7805684333667159, |
| "epoch": 0.24926278306348412, |
| "grad_norm": 93.5, |
| "learning_rate": 1.1180000000000001e-05, |
| "loss": 12.5142, |
| "mean_token_accuracy": 0.7839910417795182, |
| "num_tokens": 3719113.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.7685065409168601, |
| "epoch": 0.25371390418961776, |
| "grad_norm": 65.5, |
| "learning_rate": 1.138e-05, |
| "loss": 12.4558, |
| "mean_token_accuracy": 0.7818987771868706, |
| "num_tokens": 3785282.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.774918237887323, |
| "epoch": 0.2581650253157514, |
| "grad_norm": 61.25, |
| "learning_rate": 1.1580000000000001e-05, |
| "loss": 12.415, |
| "mean_token_accuracy": 0.7842379476875067, |
| "num_tokens": 3852276.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.7105797030963004, |
| "epoch": 0.262616146441885, |
| "grad_norm": 67.5, |
| "learning_rate": 1.178e-05, |
| "loss": 11.3721, |
| "mean_token_accuracy": 0.7995343253016471, |
| "num_tokens": 3925649.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.7462131816893816, |
| "epoch": 0.2670672675680187, |
| "grad_norm": 74.5, |
| "learning_rate": 1.198e-05, |
| "loss": 11.8831, |
| "mean_token_accuracy": 0.7898255579173565, |
| "num_tokens": 3990505.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2670672675680187, |
| "eval_biology_entropy": 1.2392896317243576, |
| "eval_biology_loss": 1.3273310661315918, |
| "eval_biology_mean_token_accuracy": 0.6752943544387817, |
| "eval_biology_num_tokens": 3990505.0, |
| "eval_biology_runtime": 36.4668, |
| "eval_biology_samples_per_second": 13.711, |
| "eval_biology_steps_per_second": 13.711, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2670672675680187, |
| "eval_chemistry_entropy": 0.7596916342377663, |
| "eval_chemistry_loss": 0.7626407742500305, |
| "eval_chemistry_mean_token_accuracy": 0.7862690081000328, |
| "eval_chemistry_num_tokens": 3990505.0, |
| "eval_chemistry_runtime": 40.266, |
| "eval_chemistry_samples_per_second": 12.417, |
| "eval_chemistry_steps_per_second": 12.417, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2670672675680187, |
| "eval_math_entropy": 0.6872916958034039, |
| "eval_math_loss": 0.8660696148872375, |
| "eval_math_mean_token_accuracy": 0.7750280216932297, |
| "eval_math_num_tokens": 3990505.0, |
| "eval_math_runtime": 41.4933, |
| "eval_math_samples_per_second": 12.05, |
| "eval_math_steps_per_second": 12.05, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2670672675680187, |
| "eval_physics_entropy": 0.7289359270334244, |
| "eval_physics_loss": 0.744917631149292, |
| "eval_physics_mean_token_accuracy": 0.7920673425793647, |
| "eval_physics_num_tokens": 3990505.0, |
| "eval_physics_runtime": 46.0067, |
| "eval_physics_samples_per_second": 10.868, |
| "eval_physics_steps_per_second": 10.868, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.7445939108729362, |
| "epoch": 0.27151838869415235, |
| "grad_norm": 65.5, |
| "learning_rate": 1.218e-05, |
| "loss": 11.9377, |
| "mean_token_accuracy": 0.790003751963377, |
| "num_tokens": 4060657.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.7278808873146773, |
| "epoch": 0.275969509820286, |
| "grad_norm": 65.0, |
| "learning_rate": 1.2380000000000002e-05, |
| "loss": 11.5778, |
| "mean_token_accuracy": 0.7942668478935957, |
| "num_tokens": 4133119.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.7475641055032611, |
| "epoch": 0.2804206309464196, |
| "grad_norm": 70.5, |
| "learning_rate": 1.2580000000000002e-05, |
| "loss": 11.9803, |
| "mean_token_accuracy": 0.7913637235760689, |
| "num_tokens": 4200051.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.7986388958990573, |
| "epoch": 0.2848717520725533, |
| "grad_norm": 71.0, |
| "learning_rate": 1.2780000000000001e-05, |
| "loss": 12.767, |
| "mean_token_accuracy": 0.782176585495472, |
| "num_tokens": 4267403.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.7370933200232684, |
| "epoch": 0.28932287319868694, |
| "grad_norm": 72.0, |
| "learning_rate": 1.2980000000000001e-05, |
| "loss": 11.8884, |
| "mean_token_accuracy": 0.7921638786792755, |
| "num_tokens": 4333268.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.737369327340275, |
| "epoch": 0.29377399432482054, |
| "grad_norm": 79.0, |
| "learning_rate": 1.3180000000000001e-05, |
| "loss": 11.7388, |
| "mean_token_accuracy": 0.7942005816847086, |
| "num_tokens": 4400242.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.7550807458348572, |
| "epoch": 0.2982251154509542, |
| "grad_norm": 74.5, |
| "learning_rate": 1.3380000000000002e-05, |
| "loss": 12.0296, |
| "mean_token_accuracy": 0.7894790366291999, |
| "num_tokens": 4464714.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.7167205691337586, |
| "epoch": 0.30267623657708786, |
| "grad_norm": 63.75, |
| "learning_rate": 1.3580000000000002e-05, |
| "loss": 11.5706, |
| "mean_token_accuracy": 0.796867698058486, |
| "num_tokens": 4535458.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.7481121812015772, |
| "epoch": 0.3071273577032215, |
| "grad_norm": 67.0, |
| "learning_rate": 1.378e-05, |
| "loss": 11.985, |
| "mean_token_accuracy": 0.7914165269583464, |
| "num_tokens": 4599099.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.7162985533475876, |
| "epoch": 0.31157847882935513, |
| "grad_norm": 56.25, |
| "learning_rate": 1.398e-05, |
| "loss": 11.4683, |
| "mean_token_accuracy": 0.7971325770020485, |
| "num_tokens": 4662903.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.31157847882935513, |
| "eval_biology_entropy": 1.2363531575202942, |
| "eval_biology_loss": 1.32443106174469, |
| "eval_biology_mean_token_accuracy": 0.6762348954081535, |
| "eval_biology_num_tokens": 4662903.0, |
| "eval_biology_runtime": 36.3542, |
| "eval_biology_samples_per_second": 13.754, |
| "eval_biology_steps_per_second": 13.754, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.31157847882935513, |
| "eval_chemistry_entropy": 0.7484616157412529, |
| "eval_chemistry_loss": 0.7520119547843933, |
| "eval_chemistry_mean_token_accuracy": 0.7884139549732209, |
| "eval_chemistry_num_tokens": 4662903.0, |
| "eval_chemistry_runtime": 41.3205, |
| "eval_chemistry_samples_per_second": 12.101, |
| "eval_chemistry_steps_per_second": 12.101, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.31157847882935513, |
| "eval_math_entropy": 0.6818331519067288, |
| "eval_math_loss": 0.862537145614624, |
| "eval_math_mean_token_accuracy": 0.7769467064142227, |
| "eval_math_num_tokens": 4662903.0, |
| "eval_math_runtime": 42.2089, |
| "eval_math_samples_per_second": 11.846, |
| "eval_math_steps_per_second": 11.846, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.31157847882935513, |
| "eval_physics_entropy": 0.7252178380489349, |
| "eval_physics_loss": 0.7445859313011169, |
| "eval_physics_mean_token_accuracy": 0.7919469431638718, |
| "eval_physics_num_tokens": 4662903.0, |
| "eval_physics_runtime": 45.6964, |
| "eval_physics_samples_per_second": 10.942, |
| "eval_physics_steps_per_second": 10.942, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.7590530560351908, |
| "epoch": 0.3160295999554888, |
| "grad_norm": 83.5, |
| "learning_rate": 1.418e-05, |
| "loss": 12.3935, |
| "mean_token_accuracy": 0.7850905049592256, |
| "num_tokens": 4729166.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.800558901950717, |
| "epoch": 0.32048072108162245, |
| "grad_norm": 79.0, |
| "learning_rate": 1.4380000000000001e-05, |
| "loss": 12.7943, |
| "mean_token_accuracy": 0.7798430301249027, |
| "num_tokens": 4796815.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.6950356176123023, |
| "epoch": 0.32493184220775606, |
| "grad_norm": 69.0, |
| "learning_rate": 1.4580000000000001e-05, |
| "loss": 11.0797, |
| "mean_token_accuracy": 0.803941647708416, |
| "num_tokens": 4865172.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.7522321011871099, |
| "epoch": 0.3293829633338897, |
| "grad_norm": 64.0, |
| "learning_rate": 1.478e-05, |
| "loss": 12.1663, |
| "mean_token_accuracy": 0.7838000770658254, |
| "num_tokens": 4932671.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.7758943744935095, |
| "epoch": 0.3338340844600234, |
| "grad_norm": 65.0, |
| "learning_rate": 1.498e-05, |
| "loss": 12.4442, |
| "mean_token_accuracy": 0.7852539490908385, |
| "num_tokens": 4998710.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.7163919297046959, |
| "epoch": 0.338285205586157, |
| "grad_norm": 67.5, |
| "learning_rate": 1.5180000000000002e-05, |
| "loss": 11.5154, |
| "mean_token_accuracy": 0.7952407207340002, |
| "num_tokens": 5066948.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.753566917218268, |
| "epoch": 0.34273632671229065, |
| "grad_norm": 67.0, |
| "learning_rate": 1.5380000000000002e-05, |
| "loss": 12.0632, |
| "mean_token_accuracy": 0.7887947488576174, |
| "num_tokens": 5129950.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.7747300613671542, |
| "epoch": 0.3471874478384243, |
| "grad_norm": 64.5, |
| "learning_rate": 1.5580000000000003e-05, |
| "loss": 12.4883, |
| "mean_token_accuracy": 0.7800568122416734, |
| "num_tokens": 5193519.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.7476665185764432, |
| "epoch": 0.351638568964558, |
| "grad_norm": 91.0, |
| "learning_rate": 1.578e-05, |
| "loss": 11.9465, |
| "mean_token_accuracy": 0.7881375091150403, |
| "num_tokens": 5256503.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.8204591780900955, |
| "epoch": 0.3560896900906916, |
| "grad_norm": 68.0, |
| "learning_rate": 1.5980000000000003e-05, |
| "loss": 13.1278, |
| "mean_token_accuracy": 0.7780214017257094, |
| "num_tokens": 5324751.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3560896900906916, |
| "eval_biology_entropy": 1.3236136644482612, |
| "eval_biology_loss": 1.3220669031143188, |
| "eval_biology_mean_token_accuracy": 0.6748943754434585, |
| "eval_biology_num_tokens": 5324751.0, |
| "eval_biology_runtime": 36.5537, |
| "eval_biology_samples_per_second": 13.679, |
| "eval_biology_steps_per_second": 13.679, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3560896900906916, |
| "eval_chemistry_entropy": 0.7881391143500804, |
| "eval_chemistry_loss": 0.7549666166305542, |
| "eval_chemistry_mean_token_accuracy": 0.7878072342276573, |
| "eval_chemistry_num_tokens": 5324751.0, |
| "eval_chemistry_runtime": 40.4688, |
| "eval_chemistry_samples_per_second": 12.355, |
| "eval_chemistry_steps_per_second": 12.355, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3560896900906916, |
| "eval_math_entropy": 0.7137112567722798, |
| "eval_math_loss": 0.8679834008216858, |
| "eval_math_mean_token_accuracy": 0.774067041516304, |
| "eval_math_num_tokens": 5324751.0, |
| "eval_math_runtime": 41.3922, |
| "eval_math_samples_per_second": 12.08, |
| "eval_math_steps_per_second": 12.08, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3560896900906916, |
| "eval_physics_entropy": 0.764995231449604, |
| "eval_physics_loss": 0.750312864780426, |
| "eval_physics_mean_token_accuracy": 0.7906691903471946, |
| "eval_physics_num_tokens": 5324751.0, |
| "eval_physics_runtime": 45.8484, |
| "eval_physics_samples_per_second": 10.906, |
| "eval_physics_steps_per_second": 10.906, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.6771990330889821, |
| "epoch": 0.36054081121682524, |
| "grad_norm": 65.0, |
| "learning_rate": 1.618e-05, |
| "loss": 11.1158, |
| "mean_token_accuracy": 0.8028291787952184, |
| "num_tokens": 5391664.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.7129247286356986, |
| "epoch": 0.3649919323429589, |
| "grad_norm": 70.5, |
| "learning_rate": 1.638e-05, |
| "loss": 11.1981, |
| "mean_token_accuracy": 0.8007186874747276, |
| "num_tokens": 5458519.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.7549328833818436, |
| "epoch": 0.3694430534690925, |
| "grad_norm": 65.0, |
| "learning_rate": 1.658e-05, |
| "loss": 12.1723, |
| "mean_token_accuracy": 0.7901175323873758, |
| "num_tokens": 5523391.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.7134035120718181, |
| "epoch": 0.37389417459522617, |
| "grad_norm": 59.0, |
| "learning_rate": 1.6780000000000002e-05, |
| "loss": 11.7326, |
| "mean_token_accuracy": 0.795387938991189, |
| "num_tokens": 5585508.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.7443888144567609, |
| "epoch": 0.37834529572135983, |
| "grad_norm": 71.0, |
| "learning_rate": 1.698e-05, |
| "loss": 11.8848, |
| "mean_token_accuracy": 0.7947730336338281, |
| "num_tokens": 5650755.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.7494110313244164, |
| "epoch": 0.38279641684749344, |
| "grad_norm": 61.5, |
| "learning_rate": 1.718e-05, |
| "loss": 11.969, |
| "mean_token_accuracy": 0.788362193852663, |
| "num_tokens": 5716321.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.7754998824559152, |
| "epoch": 0.3872475379736271, |
| "grad_norm": 67.0, |
| "learning_rate": 1.7380000000000003e-05, |
| "loss": 12.4655, |
| "mean_token_accuracy": 0.7815641265362501, |
| "num_tokens": 5782698.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.7258908217772841, |
| "epoch": 0.39169865909976076, |
| "grad_norm": 54.5, |
| "learning_rate": 1.758e-05, |
| "loss": 11.662, |
| "mean_token_accuracy": 0.7951392225921154, |
| "num_tokens": 5848889.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.7699500862509012, |
| "epoch": 0.3961497802258944, |
| "grad_norm": 65.5, |
| "learning_rate": 1.7780000000000003e-05, |
| "loss": 12.5712, |
| "mean_token_accuracy": 0.7857454361394047, |
| "num_tokens": 5912919.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.7454446164891124, |
| "epoch": 0.400600901352028, |
| "grad_norm": 60.75, |
| "learning_rate": 1.798e-05, |
| "loss": 11.8793, |
| "mean_token_accuracy": 0.793294046446681, |
| "num_tokens": 5980229.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.400600901352028, |
| "eval_biology_entropy": 1.2526325694918632, |
| "eval_biology_loss": 1.3328229188919067, |
| "eval_biology_mean_token_accuracy": 0.6739730868339538, |
| "eval_biology_num_tokens": 5980229.0, |
| "eval_biology_runtime": 37.1628, |
| "eval_biology_samples_per_second": 13.454, |
| "eval_biology_steps_per_second": 13.454, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.400600901352028, |
| "eval_chemistry_entropy": 0.7478999142050743, |
| "eval_chemistry_loss": 0.7579869627952576, |
| "eval_chemistry_mean_token_accuracy": 0.7872751998305321, |
| "eval_chemistry_num_tokens": 5980229.0, |
| "eval_chemistry_runtime": 41.0567, |
| "eval_chemistry_samples_per_second": 12.178, |
| "eval_chemistry_steps_per_second": 12.178, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.400600901352028, |
| "eval_math_entropy": 0.691623161137104, |
| "eval_math_loss": 0.8888975977897644, |
| "eval_math_mean_token_accuracy": 0.7720628465414048, |
| "eval_math_num_tokens": 5980229.0, |
| "eval_math_runtime": 41.3967, |
| "eval_math_samples_per_second": 12.078, |
| "eval_math_steps_per_second": 12.078, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.400600901352028, |
| "eval_physics_entropy": 0.7361411595344544, |
| "eval_physics_loss": 0.7520632743835449, |
| "eval_physics_mean_token_accuracy": 0.7907493528723717, |
| "eval_physics_num_tokens": 5980229.0, |
| "eval_physics_runtime": 46.0024, |
| "eval_physics_samples_per_second": 10.869, |
| "eval_physics_steps_per_second": 10.869, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.7022204802371561, |
| "epoch": 0.4050520224781617, |
| "grad_norm": 61.0, |
| "learning_rate": 1.8180000000000002e-05, |
| "loss": 11.4405, |
| "mean_token_accuracy": 0.798212106898427, |
| "num_tokens": 6048508.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 0.7361409039236605, |
| "epoch": 0.40950314360429535, |
| "grad_norm": 60.25, |
| "learning_rate": 1.8380000000000004e-05, |
| "loss": 11.7212, |
| "mean_token_accuracy": 0.7943942189216614, |
| "num_tokens": 6114855.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 0.7555323796346783, |
| "epoch": 0.41395426473042896, |
| "grad_norm": 54.0, |
| "learning_rate": 1.858e-05, |
| "loss": 12.1222, |
| "mean_token_accuracy": 0.7887333419173956, |
| "num_tokens": 6179050.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 0.7449197143316268, |
| "epoch": 0.4184053858565626, |
| "grad_norm": 59.0, |
| "learning_rate": 1.878e-05, |
| "loss": 12.1501, |
| "mean_token_accuracy": 0.7886579774320126, |
| "num_tokens": 6244987.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 0.7183629649691283, |
| "epoch": 0.4228565069826963, |
| "grad_norm": 66.0, |
| "learning_rate": 1.898e-05, |
| "loss": 11.6027, |
| "mean_token_accuracy": 0.794747618958354, |
| "num_tokens": 6310799.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.7170003782957792, |
| "epoch": 0.4273076281088299, |
| "grad_norm": 63.5, |
| "learning_rate": 1.918e-05, |
| "loss": 11.5812, |
| "mean_token_accuracy": 0.7965250793844462, |
| "num_tokens": 6378152.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 0.7422669138759375, |
| "epoch": 0.43175874923496355, |
| "grad_norm": 54.0, |
| "learning_rate": 1.938e-05, |
| "loss": 11.7787, |
| "mean_token_accuracy": 0.7933820992708206, |
| "num_tokens": 6442491.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 0.7739317396655678, |
| "epoch": 0.4362098703610972, |
| "grad_norm": 57.75, |
| "learning_rate": 1.9580000000000002e-05, |
| "loss": 12.5927, |
| "mean_token_accuracy": 0.7841954406350851, |
| "num_tokens": 6510231.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 0.745883577503264, |
| "epoch": 0.44066099148723087, |
| "grad_norm": 57.25, |
| "learning_rate": 1.978e-05, |
| "loss": 12.0418, |
| "mean_token_accuracy": 0.790126183629036, |
| "num_tokens": 6572858.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 0.7626472780480981, |
| "epoch": 0.4451121126133645, |
| "grad_norm": 48.0, |
| "learning_rate": 1.9980000000000002e-05, |
| "loss": 12.3648, |
| "mean_token_accuracy": 0.7834480810910464, |
| "num_tokens": 6637273.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4451121126133645, |
| "eval_biology_entropy": 1.2697618773579598, |
| "eval_biology_loss": 1.3405715227127075, |
| "eval_biology_mean_token_accuracy": 0.6724427245259285, |
| "eval_biology_num_tokens": 6637273.0, |
| "eval_biology_runtime": 34.6717, |
| "eval_biology_samples_per_second": 14.421, |
| "eval_biology_steps_per_second": 14.421, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4451121126133645, |
| "eval_chemistry_entropy": 0.7615428499877452, |
| "eval_chemistry_loss": 0.7553035616874695, |
| "eval_chemistry_mean_token_accuracy": 0.7880414368510247, |
| "eval_chemistry_num_tokens": 6637273.0, |
| "eval_chemistry_runtime": 38.9404, |
| "eval_chemistry_samples_per_second": 12.84, |
| "eval_chemistry_steps_per_second": 12.84, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4451121126133645, |
| "eval_math_entropy": 0.7116467788815498, |
| "eval_math_loss": 0.8722440004348755, |
| "eval_math_mean_token_accuracy": 0.7725971038341523, |
| "eval_math_num_tokens": 6637273.0, |
| "eval_math_runtime": 39.9329, |
| "eval_math_samples_per_second": 12.521, |
| "eval_math_steps_per_second": 12.521, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4451121126133645, |
| "eval_physics_entropy": 0.7675083922743797, |
| "eval_physics_loss": 0.7605612874031067, |
| "eval_physics_mean_token_accuracy": 0.7887651996016503, |
| "eval_physics_num_tokens": 6637273.0, |
| "eval_physics_runtime": 44.6453, |
| "eval_physics_samples_per_second": 11.199, |
| "eval_physics_steps_per_second": 11.199, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.7314162964001298, |
| "epoch": 0.44956323373949814, |
| "grad_norm": 57.5, |
| "learning_rate": 1.9980000000000002e-05, |
| "loss": 11.7366, |
| "mean_token_accuracy": 0.7923816435039044, |
| "num_tokens": 6700799.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 0.7421712795272469, |
| "epoch": 0.4540143548656318, |
| "grad_norm": 57.5, |
| "learning_rate": 1.995777777777778e-05, |
| "loss": 12.1497, |
| "mean_token_accuracy": 0.7892091479152441, |
| "num_tokens": 6765798.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 0.6979273453354835, |
| "epoch": 0.4584654759917654, |
| "grad_norm": 58.5, |
| "learning_rate": 1.9935555555555557e-05, |
| "loss": 11.3013, |
| "mean_token_accuracy": 0.7992341227829456, |
| "num_tokens": 6832774.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 0.7764921618625522, |
| "epoch": 0.46291659711789906, |
| "grad_norm": 56.5, |
| "learning_rate": 1.9913333333333335e-05, |
| "loss": 12.4581, |
| "mean_token_accuracy": 0.783613259345293, |
| "num_tokens": 6896684.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 0.7277746710926294, |
| "epoch": 0.4673677182440327, |
| "grad_norm": 57.75, |
| "learning_rate": 1.9891111111111112e-05, |
| "loss": 11.7064, |
| "mean_token_accuracy": 0.798894327133894, |
| "num_tokens": 6964423.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.7224507334642112, |
| "epoch": 0.4718188393701664, |
| "grad_norm": 52.75, |
| "learning_rate": 1.986888888888889e-05, |
| "loss": 11.8859, |
| "mean_token_accuracy": 0.7931920390576124, |
| "num_tokens": 7033417.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 0.7771790644153953, |
| "epoch": 0.4762699604963, |
| "grad_norm": 55.0, |
| "learning_rate": 1.9846666666666668e-05, |
| "loss": 12.3152, |
| "mean_token_accuracy": 0.7860798113048076, |
| "num_tokens": 7101274.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 0.7393451489508152, |
| "epoch": 0.48072108162243365, |
| "grad_norm": 52.5, |
| "learning_rate": 1.9824444444444445e-05, |
| "loss": 12.1816, |
| "mean_token_accuracy": 0.7896892268210649, |
| "num_tokens": 7166608.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 0.7223112307488918, |
| "epoch": 0.4851722027485673, |
| "grad_norm": 72.0, |
| "learning_rate": 1.9802222222222226e-05, |
| "loss": 11.573, |
| "mean_token_accuracy": 0.7999571479856968, |
| "num_tokens": 7240958.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 0.7434121018275619, |
| "epoch": 0.4896233238747009, |
| "grad_norm": 55.0, |
| "learning_rate": 1.978e-05, |
| "loss": 11.995, |
| "mean_token_accuracy": 0.7897290639579296, |
| "num_tokens": 7311968.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4896233238747009, |
| "eval_biology_entropy": 1.2825020100474358, |
| "eval_biology_loss": 1.3549916744232178, |
| "eval_biology_mean_token_accuracy": 0.6708763095140458, |
| "eval_biology_num_tokens": 7311968.0, |
| "eval_biology_runtime": 34.7487, |
| "eval_biology_samples_per_second": 14.389, |
| "eval_biology_steps_per_second": 14.389, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4896233238747009, |
| "eval_chemistry_entropy": 0.7363105757832528, |
| "eval_chemistry_loss": 0.7509695887565613, |
| "eval_chemistry_mean_token_accuracy": 0.7897556048631668, |
| "eval_chemistry_num_tokens": 7311968.0, |
| "eval_chemistry_runtime": 39.5761, |
| "eval_chemistry_samples_per_second": 12.634, |
| "eval_chemistry_steps_per_second": 12.634, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4896233238747009, |
| "eval_math_entropy": 0.6904492176771164, |
| "eval_math_loss": 0.8790993690490723, |
| "eval_math_mean_token_accuracy": 0.7729596102237701, |
| "eval_math_num_tokens": 7311968.0, |
| "eval_math_runtime": 40.1018, |
| "eval_math_samples_per_second": 12.468, |
| "eval_math_steps_per_second": 12.468, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4896233238747009, |
| "eval_physics_entropy": 0.7335765887498855, |
| "eval_physics_loss": 0.7572531700134277, |
| "eval_physics_mean_token_accuracy": 0.7901599068641663, |
| "eval_physics_num_tokens": 7311968.0, |
| "eval_physics_runtime": 44.6604, |
| "eval_physics_samples_per_second": 11.196, |
| "eval_physics_steps_per_second": 11.196, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.7318524705246091, |
| "epoch": 0.4940744450008346, |
| "grad_norm": 60.75, |
| "learning_rate": 1.975777777777778e-05, |
| "loss": 11.7678, |
| "mean_token_accuracy": 0.7911851242184639, |
| "num_tokens": 7378961.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 0.7082980162464082, |
| "epoch": 0.49852556612696824, |
| "grad_norm": 61.75, |
| "learning_rate": 1.9735555555555556e-05, |
| "loss": 11.4456, |
| "mean_token_accuracy": 0.7980625631287694, |
| "num_tokens": 7444923.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 0.7435412630438805, |
| "epoch": 0.5029766872531019, |
| "grad_norm": 55.5, |
| "learning_rate": 1.9713333333333337e-05, |
| "loss": 11.7624, |
| "mean_token_accuracy": 0.7926325134932994, |
| "num_tokens": 7509885.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 0.7542540356516838, |
| "epoch": 0.5074278083792355, |
| "grad_norm": 54.0, |
| "learning_rate": 1.969111111111111e-05, |
| "loss": 12.4162, |
| "mean_token_accuracy": 0.7846910808235407, |
| "num_tokens": 7576456.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 0.7760613728314638, |
| "epoch": 0.5118789295053692, |
| "grad_norm": 57.0, |
| "learning_rate": 1.9668888888888892e-05, |
| "loss": 12.3585, |
| "mean_token_accuracy": 0.7867991000413894, |
| "num_tokens": 7641821.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.7095673834905029, |
| "epoch": 0.5163300506315028, |
| "grad_norm": 54.5, |
| "learning_rate": 1.9646666666666666e-05, |
| "loss": 11.5013, |
| "mean_token_accuracy": 0.7958923596888781, |
| "num_tokens": 7706502.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 0.8006078721955419, |
| "epoch": 0.5207811717576365, |
| "grad_norm": 64.5, |
| "learning_rate": 1.9624444444444447e-05, |
| "loss": 12.8183, |
| "mean_token_accuracy": 0.7838775899261237, |
| "num_tokens": 7772353.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 0.7142350310459733, |
| "epoch": 0.52523229288377, |
| "grad_norm": 50.25, |
| "learning_rate": 1.9602222222222225e-05, |
| "loss": 11.7207, |
| "mean_token_accuracy": 0.795654509216547, |
| "num_tokens": 7838516.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 0.7257593980059027, |
| "epoch": 0.5296834140099037, |
| "grad_norm": 61.25, |
| "learning_rate": 1.9580000000000002e-05, |
| "loss": 11.5084, |
| "mean_token_accuracy": 0.7954147141426802, |
| "num_tokens": 7902568.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 0.7607359967194498, |
| "epoch": 0.5341345351360374, |
| "grad_norm": 54.25, |
| "learning_rate": 1.955777777777778e-05, |
| "loss": 12.0382, |
| "mean_token_accuracy": 0.788224334642291, |
| "num_tokens": 7969704.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.5341345351360374, |
| "eval_biology_entropy": 1.2328835948705674, |
| "eval_biology_loss": 1.3470529317855835, |
| "eval_biology_mean_token_accuracy": 0.6719091883301735, |
| "eval_biology_num_tokens": 7969704.0, |
| "eval_biology_runtime": 34.5402, |
| "eval_biology_samples_per_second": 14.476, |
| "eval_biology_steps_per_second": 14.476, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.5341345351360374, |
| "eval_chemistry_entropy": 0.727981344461441, |
| "eval_chemistry_loss": 0.7450346946716309, |
| "eval_chemistry_mean_token_accuracy": 0.7906108702421188, |
| "eval_chemistry_num_tokens": 7969704.0, |
| "eval_chemistry_runtime": 39.3686, |
| "eval_chemistry_samples_per_second": 12.7, |
| "eval_chemistry_steps_per_second": 12.7, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.5341345351360374, |
| "eval_math_entropy": 0.6775654193758964, |
| "eval_math_loss": 0.8872368931770325, |
| "eval_math_mean_token_accuracy": 0.7717010715007782, |
| "eval_math_num_tokens": 7969704.0, |
| "eval_math_runtime": 40.8591, |
| "eval_math_samples_per_second": 12.237, |
| "eval_math_steps_per_second": 12.237, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.5341345351360374, |
| "eval_physics_entropy": 0.728905067563057, |
| "eval_physics_loss": 0.7556765079498291, |
| "eval_physics_mean_token_accuracy": 0.7903099409341812, |
| "eval_physics_num_tokens": 7969704.0, |
| "eval_physics_runtime": 44.9155, |
| "eval_physics_samples_per_second": 11.132, |
| "eval_physics_steps_per_second": 11.132, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.6951992505230009, |
| "epoch": 0.538585656262171, |
| "grad_norm": 48.0, |
| "learning_rate": 1.9535555555555557e-05, |
| "loss": 11.4334, |
| "mean_token_accuracy": 0.7958714343607426, |
| "num_tokens": 8034765.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 0.7527200236916542, |
| "epoch": 0.5430367773883047, |
| "grad_norm": 45.75, |
| "learning_rate": 1.9513333333333335e-05, |
| "loss": 11.9919, |
| "mean_token_accuracy": 0.7917780404910445, |
| "num_tokens": 8103869.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 0.686318707279861, |
| "epoch": 0.5474878985144384, |
| "grad_norm": 44.25, |
| "learning_rate": 1.9491111111111113e-05, |
| "loss": 11.1097, |
| "mean_token_accuracy": 0.8036415990442037, |
| "num_tokens": 8173386.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 0.7415073176845908, |
| "epoch": 0.551939019640572, |
| "grad_norm": 53.75, |
| "learning_rate": 1.946888888888889e-05, |
| "loss": 11.8806, |
| "mean_token_accuracy": 0.7891732029616833, |
| "num_tokens": 8242162.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 0.7266354532912374, |
| "epoch": 0.5563901407667056, |
| "grad_norm": 61.0, |
| "learning_rate": 1.9446666666666668e-05, |
| "loss": 11.6483, |
| "mean_token_accuracy": 0.7947042044252157, |
| "num_tokens": 8308919.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.7407059632241726, |
| "epoch": 0.5608412618928392, |
| "grad_norm": 67.0, |
| "learning_rate": 1.9424444444444446e-05, |
| "loss": 12.0106, |
| "mean_token_accuracy": 0.7900955501943827, |
| "num_tokens": 8365617.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 0.7527385540306568, |
| "epoch": 0.5652923830189729, |
| "grad_norm": 48.0, |
| "learning_rate": 1.9402222222222223e-05, |
| "loss": 11.9171, |
| "mean_token_accuracy": 0.7914537958800792, |
| "num_tokens": 8430728.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 0.7172600775957108, |
| "epoch": 0.5697435041451065, |
| "grad_norm": 49.25, |
| "learning_rate": 1.938e-05, |
| "loss": 11.5836, |
| "mean_token_accuracy": 0.7958250787109137, |
| "num_tokens": 8497852.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 0.7470160932280123, |
| "epoch": 0.5741946252712402, |
| "grad_norm": 50.0, |
| "learning_rate": 1.935777777777778e-05, |
| "loss": 12.1357, |
| "mean_token_accuracy": 0.7876220095902682, |
| "num_tokens": 8558952.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 0.7452291272580623, |
| "epoch": 0.5786457463973739, |
| "grad_norm": 57.75, |
| "learning_rate": 1.9335555555555556e-05, |
| "loss": 11.8494, |
| "mean_token_accuracy": 0.7954678740352392, |
| "num_tokens": 8622868.0, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.5786457463973739, |
| "eval_biology_entropy": 1.270399274289608, |
| "eval_biology_loss": 1.3523783683776855, |
| "eval_biology_mean_token_accuracy": 0.6706679166555405, |
| "eval_biology_num_tokens": 8622868.0, |
| "eval_biology_runtime": 35.3016, |
| "eval_biology_samples_per_second": 14.164, |
| "eval_biology_steps_per_second": 14.164, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.5786457463973739, |
| "eval_chemistry_entropy": 0.7226660187542439, |
| "eval_chemistry_loss": 0.7358337640762329, |
| "eval_chemistry_mean_token_accuracy": 0.7928519014120102, |
| "eval_chemistry_num_tokens": 8622868.0, |
| "eval_chemistry_runtime": 39.6574, |
| "eval_chemistry_samples_per_second": 12.608, |
| "eval_chemistry_steps_per_second": 12.608, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.5786457463973739, |
| "eval_math_entropy": 0.6689038871824742, |
| "eval_math_loss": 0.8895673155784607, |
| "eval_math_mean_token_accuracy": 0.7727138675451278, |
| "eval_math_num_tokens": 8622868.0, |
| "eval_math_runtime": 40.5077, |
| "eval_math_samples_per_second": 12.343, |
| "eval_math_steps_per_second": 12.343, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.5786457463973739, |
| "eval_physics_entropy": 0.7133040081262588, |
| "eval_physics_loss": 0.7542717456817627, |
| "eval_physics_mean_token_accuracy": 0.7914812366366386, |
| "eval_physics_num_tokens": 8622868.0, |
| "eval_physics_runtime": 44.946, |
| "eval_physics_samples_per_second": 11.124, |
| "eval_physics_steps_per_second": 11.124, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.6984654633328319, |
| "epoch": 0.5830968675235075, |
| "grad_norm": 55.75, |
| "learning_rate": 1.9313333333333334e-05, |
| "loss": 11.4106, |
| "mean_token_accuracy": 0.7972324814647436, |
| "num_tokens": 8694510.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 0.7897671807557345, |
| "epoch": 0.5875479886496411, |
| "grad_norm": 65.0, |
| "learning_rate": 1.9291111111111115e-05, |
| "loss": 12.6834, |
| "mean_token_accuracy": 0.7794294957071543, |
| "num_tokens": 8757753.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 0.7390378901734949, |
| "epoch": 0.5919991097757747, |
| "grad_norm": 51.0, |
| "learning_rate": 1.926888888888889e-05, |
| "loss": 11.8734, |
| "mean_token_accuracy": 0.7966042939573527, |
| "num_tokens": 8823153.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 0.7496651741676033, |
| "epoch": 0.5964502309019084, |
| "grad_norm": 53.25, |
| "learning_rate": 1.924666666666667e-05, |
| "loss": 12.1236, |
| "mean_token_accuracy": 0.788444896414876, |
| "num_tokens": 8886401.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 0.7156450959853828, |
| "epoch": 0.6009013520280421, |
| "grad_norm": 45.75, |
| "learning_rate": 1.9224444444444444e-05, |
| "loss": 11.4242, |
| "mean_token_accuracy": 0.7963771104812623, |
| "num_tokens": 8958530.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.7286824054084718, |
| "epoch": 0.6053524731541757, |
| "grad_norm": 55.0, |
| "learning_rate": 1.9202222222222225e-05, |
| "loss": 11.7964, |
| "mean_token_accuracy": 0.7932926584035158, |
| "num_tokens": 9024677.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 0.7564192423596978, |
| "epoch": 0.6098035942803094, |
| "grad_norm": 52.25, |
| "learning_rate": 1.918e-05, |
| "loss": 11.9791, |
| "mean_token_accuracy": 0.790202745422721, |
| "num_tokens": 9090280.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 0.7076619225554168, |
| "epoch": 0.614254715406443, |
| "grad_norm": 52.75, |
| "learning_rate": 1.915777777777778e-05, |
| "loss": 11.5864, |
| "mean_token_accuracy": 0.7959123384207487, |
| "num_tokens": 9153771.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 0.6782314692623913, |
| "epoch": 0.6187058365325766, |
| "grad_norm": 47.5, |
| "learning_rate": 1.9135555555555555e-05, |
| "loss": 10.7507, |
| "mean_token_accuracy": 0.8093214847147465, |
| "num_tokens": 9227117.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 0.7308899962343276, |
| "epoch": 0.6231569576587103, |
| "grad_norm": 50.25, |
| "learning_rate": 1.9113333333333336e-05, |
| "loss": 11.9294, |
| "mean_token_accuracy": 0.790796834975481, |
| "num_tokens": 9291760.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.6231569576587103, |
| "eval_biology_entropy": 1.2965683770179748, |
| "eval_biology_loss": 1.3410367965698242, |
| "eval_biology_mean_token_accuracy": 0.6702442263960838, |
| "eval_biology_num_tokens": 9291760.0, |
| "eval_biology_runtime": 35.3518, |
| "eval_biology_samples_per_second": 14.144, |
| "eval_biology_steps_per_second": 14.144, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.6231569576587103, |
| "eval_chemistry_entropy": 0.7365462110638619, |
| "eval_chemistry_loss": 0.7281596660614014, |
| "eval_chemistry_mean_token_accuracy": 0.7939923223257065, |
| "eval_chemistry_num_tokens": 9291760.0, |
| "eval_chemistry_runtime": 39.6432, |
| "eval_chemistry_samples_per_second": 12.613, |
| "eval_chemistry_steps_per_second": 12.613, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.6231569576587103, |
| "eval_math_entropy": 0.7127760598063468, |
| "eval_math_loss": 0.8852732181549072, |
| "eval_math_mean_token_accuracy": 0.772164557814598, |
| "eval_math_num_tokens": 9291760.0, |
| "eval_math_runtime": 40.409, |
| "eval_math_samples_per_second": 12.373, |
| "eval_math_steps_per_second": 12.373, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.6231569576587103, |
| "eval_physics_entropy": 0.7410066242218017, |
| "eval_physics_loss": 0.7547739148139954, |
| "eval_physics_mean_token_accuracy": 0.7911624670028686, |
| "eval_physics_num_tokens": 9291760.0, |
| "eval_physics_runtime": 45.0651, |
| "eval_physics_samples_per_second": 11.095, |
| "eval_physics_steps_per_second": 11.095, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.764516063220799, |
| "epoch": 0.6276080787848439, |
| "grad_norm": 51.25, |
| "learning_rate": 1.9091111111111113e-05, |
| "loss": 12.1236, |
| "mean_token_accuracy": 0.7861191317439079, |
| "num_tokens": 9357561.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 0.7065011899918318, |
| "epoch": 0.6320591999109776, |
| "grad_norm": 56.0, |
| "learning_rate": 1.906888888888889e-05, |
| "loss": 11.5089, |
| "mean_token_accuracy": 0.798106643371284, |
| "num_tokens": 9425022.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 0.7121715405024588, |
| "epoch": 0.6365103210371112, |
| "grad_norm": 56.25, |
| "learning_rate": 1.904666666666667e-05, |
| "loss": 11.3189, |
| "mean_token_accuracy": 0.8004428222775459, |
| "num_tokens": 9492028.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 0.6874197697266936, |
| "epoch": 0.6409614421632449, |
| "grad_norm": 53.25, |
| "learning_rate": 1.9024444444444446e-05, |
| "loss": 11.048, |
| "mean_token_accuracy": 0.8003636717796325, |
| "num_tokens": 9561091.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 0.7115700559690594, |
| "epoch": 0.6454125632893785, |
| "grad_norm": 51.25, |
| "learning_rate": 1.9002222222222224e-05, |
| "loss": 11.3964, |
| "mean_token_accuracy": 0.7977115370333194, |
| "num_tokens": 9628383.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.6615842315368354, |
| "epoch": 0.6498636844155121, |
| "grad_norm": 46.25, |
| "learning_rate": 1.898e-05, |
| "loss": 10.652, |
| "mean_token_accuracy": 0.8100770756602287, |
| "num_tokens": 9695723.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 0.6988324311561882, |
| "epoch": 0.6543148055416458, |
| "grad_norm": 48.5, |
| "learning_rate": 1.895777777777778e-05, |
| "loss": 11.2433, |
| "mean_token_accuracy": 0.8033667050302029, |
| "num_tokens": 9763393.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 0.740055176243186, |
| "epoch": 0.6587659266677794, |
| "grad_norm": 45.75, |
| "learning_rate": 1.8935555555555556e-05, |
| "loss": 11.6971, |
| "mean_token_accuracy": 0.7966903638094663, |
| "num_tokens": 9827272.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 0.6889881357550621, |
| "epoch": 0.6632170477939131, |
| "grad_norm": 47.75, |
| "learning_rate": 1.8913333333333334e-05, |
| "loss": 11.1825, |
| "mean_token_accuracy": 0.8002750147134066, |
| "num_tokens": 9892418.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 0.6946229469962418, |
| "epoch": 0.6676681689200468, |
| "grad_norm": 48.75, |
| "learning_rate": 1.8891111111111115e-05, |
| "loss": 11.1311, |
| "mean_token_accuracy": 0.802448557689786, |
| "num_tokens": 9955369.0, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6676681689200468, |
| "eval_biology_entropy": 1.225859948515892, |
| "eval_biology_loss": 1.344753384590149, |
| "eval_biology_mean_token_accuracy": 0.6716743484735489, |
| "eval_biology_num_tokens": 9955369.0, |
| "eval_biology_runtime": 35.0712, |
| "eval_biology_samples_per_second": 14.257, |
| "eval_biology_steps_per_second": 14.257, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6676681689200468, |
| "eval_chemistry_entropy": 0.6977527342438697, |
| "eval_chemistry_loss": 0.7168055176734924, |
| "eval_chemistry_mean_token_accuracy": 0.7972170073986053, |
| "eval_chemistry_num_tokens": 9955369.0, |
| "eval_chemistry_runtime": 39.4894, |
| "eval_chemistry_samples_per_second": 12.662, |
| "eval_chemistry_steps_per_second": 12.662, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6676681689200468, |
| "eval_math_entropy": 0.670133613884449, |
| "eval_math_loss": 0.8919703960418701, |
| "eval_math_mean_token_accuracy": 0.7722328932285308, |
| "eval_math_num_tokens": 9955369.0, |
| "eval_math_runtime": 40.4938, |
| "eval_math_samples_per_second": 12.348, |
| "eval_math_steps_per_second": 12.348, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6676681689200468, |
| "eval_physics_entropy": 0.7054080674946308, |
| "eval_physics_loss": 0.7483915090560913, |
| "eval_physics_mean_token_accuracy": 0.7919600957632065, |
| "eval_physics_num_tokens": 9955369.0, |
| "eval_physics_runtime": 44.9964, |
| "eval_physics_samples_per_second": 11.112, |
| "eval_physics_steps_per_second": 11.112, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.7044103164225817, |
| "epoch": 0.6721192900461804, |
| "grad_norm": 59.0, |
| "learning_rate": 1.886888888888889e-05, |
| "loss": 11.356, |
| "mean_token_accuracy": 0.7981578037142754, |
| "num_tokens": 10026298.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 0.6750010882504285, |
| "epoch": 0.676570411172314, |
| "grad_norm": 48.5, |
| "learning_rate": 1.884666666666667e-05, |
| "loss": 10.656, |
| "mean_token_accuracy": 0.8101748798042536, |
| "num_tokens": 10096065.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 0.6924384200014174, |
| "epoch": 0.6810215322984476, |
| "grad_norm": 51.25, |
| "learning_rate": 1.8824444444444445e-05, |
| "loss": 11.3517, |
| "mean_token_accuracy": 0.8001077000051737, |
| "num_tokens": 10160745.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 0.673445784766227, |
| "epoch": 0.6854726534245813, |
| "grad_norm": 46.75, |
| "learning_rate": 1.8802222222222226e-05, |
| "loss": 10.659, |
| "mean_token_accuracy": 0.8083447456359864, |
| "num_tokens": 10233806.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 0.6894099942408503, |
| "epoch": 0.689923774550715, |
| "grad_norm": 56.75, |
| "learning_rate": 1.878e-05, |
| "loss": 11.2095, |
| "mean_token_accuracy": 0.8019303198903799, |
| "num_tokens": 10298845.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.6929447575472295, |
| "epoch": 0.6943748956768486, |
| "grad_norm": 49.25, |
| "learning_rate": 1.875777777777778e-05, |
| "loss": 11.0324, |
| "mean_token_accuracy": 0.8037194091826677, |
| "num_tokens": 10364601.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 0.6951657691970468, |
| "epoch": 0.6988260168029823, |
| "grad_norm": 52.0, |
| "learning_rate": 1.873555555555556e-05, |
| "loss": 11.2917, |
| "mean_token_accuracy": 0.7976405322551727, |
| "num_tokens": 10434433.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 0.7162799044512212, |
| "epoch": 0.703277137929116, |
| "grad_norm": 55.75, |
| "learning_rate": 1.8713333333333336e-05, |
| "loss": 11.4194, |
| "mean_token_accuracy": 0.79690898694098, |
| "num_tokens": 10500891.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 0.7040263103321195, |
| "epoch": 0.7077282590552495, |
| "grad_norm": 49.0, |
| "learning_rate": 1.8691111111111114e-05, |
| "loss": 11.4425, |
| "mean_token_accuracy": 0.8009267061948776, |
| "num_tokens": 10567784.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 0.7154285722412169, |
| "epoch": 0.7121793801813832, |
| "grad_norm": 45.5, |
| "learning_rate": 1.866888888888889e-05, |
| "loss": 11.2045, |
| "mean_token_accuracy": 0.8016629904508591, |
| "num_tokens": 10633325.0, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.7121793801813832, |
| "eval_biology_entropy": 1.2686697797775268, |
| "eval_biology_loss": 1.3475232124328613, |
| "eval_biology_mean_token_accuracy": 0.6715757512450218, |
| "eval_biology_num_tokens": 10633325.0, |
| "eval_biology_runtime": 37.2608, |
| "eval_biology_samples_per_second": 13.419, |
| "eval_biology_steps_per_second": 13.419, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.7121793801813832, |
| "eval_chemistry_entropy": 0.7082813937962055, |
| "eval_chemistry_loss": 0.709429144859314, |
| "eval_chemistry_mean_token_accuracy": 0.7980507612228394, |
| "eval_chemistry_num_tokens": 10633325.0, |
| "eval_chemistry_runtime": 41.5255, |
| "eval_chemistry_samples_per_second": 12.041, |
| "eval_chemistry_steps_per_second": 12.041, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.7121793801813832, |
| "eval_math_entropy": 0.700207156687975, |
| "eval_math_loss": 0.8887552618980408, |
| "eval_math_mean_token_accuracy": 0.7707038291096687, |
| "eval_math_num_tokens": 10633325.0, |
| "eval_math_runtime": 41.5728, |
| "eval_math_samples_per_second": 12.027, |
| "eval_math_steps_per_second": 12.027, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.7121793801813832, |
| "eval_physics_entropy": 0.7126084741950035, |
| "eval_physics_loss": 0.7438511848449707, |
| "eval_physics_mean_token_accuracy": 0.7933549825549125, |
| "eval_physics_num_tokens": 10633325.0, |
| "eval_physics_runtime": 45.9285, |
| "eval_physics_samples_per_second": 10.886, |
| "eval_physics_steps_per_second": 10.886, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.6555963907390833, |
| "epoch": 0.7166305013075168, |
| "grad_norm": 46.75, |
| "learning_rate": 1.864666666666667e-05, |
| "loss": 10.7285, |
| "mean_token_accuracy": 0.8088797086849808, |
| "num_tokens": 10699737.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 0.622994406428188, |
| "epoch": 0.7210816224336505, |
| "grad_norm": 54.0, |
| "learning_rate": 1.8624444444444446e-05, |
| "loss": 9.9832, |
| "mean_token_accuracy": 0.818326310813427, |
| "num_tokens": 10764319.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 0.7015501054003834, |
| "epoch": 0.7255327435597841, |
| "grad_norm": 49.0, |
| "learning_rate": 1.8602222222222224e-05, |
| "loss": 11.2865, |
| "mean_token_accuracy": 0.79976800493896, |
| "num_tokens": 10831617.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 0.717830996774137, |
| "epoch": 0.7299838646859178, |
| "grad_norm": 58.25, |
| "learning_rate": 1.858e-05, |
| "loss": 11.4257, |
| "mean_token_accuracy": 0.8004014391452074, |
| "num_tokens": 10897916.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 0.6889832572080195, |
| "epoch": 0.7344349858120514, |
| "grad_norm": 48.0, |
| "learning_rate": 1.855777777777778e-05, |
| "loss": 11.124, |
| "mean_token_accuracy": 0.8024733573198318, |
| "num_tokens": 10965483.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.7227079953998328, |
| "epoch": 0.738886106938185, |
| "grad_norm": 47.5, |
| "learning_rate": 1.8535555555555557e-05, |
| "loss": 11.6312, |
| "mean_token_accuracy": 0.7963551234453916, |
| "num_tokens": 11030485.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 0.6877313646487891, |
| "epoch": 0.7433372280643187, |
| "grad_norm": 51.25, |
| "learning_rate": 1.8513333333333335e-05, |
| "loss": 11.0117, |
| "mean_token_accuracy": 0.8049852427095174, |
| "num_tokens": 11097108.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 0.6374788259156048, |
| "epoch": 0.7477883491904523, |
| "grad_norm": 48.5, |
| "learning_rate": 1.8491111111111112e-05, |
| "loss": 10.4188, |
| "mean_token_accuracy": 0.8140723098069429, |
| "num_tokens": 11165356.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 0.7090142169035971, |
| "epoch": 0.752239470316586, |
| "grad_norm": 46.25, |
| "learning_rate": 1.846888888888889e-05, |
| "loss": 11.254, |
| "mean_token_accuracy": 0.8003898195922374, |
| "num_tokens": 11234429.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 0.6993439633399248, |
| "epoch": 0.7566905914427197, |
| "grad_norm": 49.0, |
| "learning_rate": 1.8446666666666667e-05, |
| "loss": 11.1632, |
| "mean_token_accuracy": 0.8017345808446408, |
| "num_tokens": 11299223.0, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.7566905914427197, |
| "eval_biology_entropy": 1.2939974426627159, |
| "eval_biology_loss": 1.3418560028076172, |
| "eval_biology_mean_token_accuracy": 0.6719679839015007, |
| "eval_biology_num_tokens": 11299223.0, |
| "eval_biology_runtime": 37.3694, |
| "eval_biology_samples_per_second": 13.38, |
| "eval_biology_steps_per_second": 13.38, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.7566905914427197, |
| "eval_chemistry_entropy": 0.6994238477945328, |
| "eval_chemistry_loss": 0.7064142227172852, |
| "eval_chemistry_mean_token_accuracy": 0.799383031964302, |
| "eval_chemistry_num_tokens": 11299223.0, |
| "eval_chemistry_runtime": 41.2811, |
| "eval_chemistry_samples_per_second": 12.112, |
| "eval_chemistry_steps_per_second": 12.112, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.7566905914427197, |
| "eval_math_entropy": 0.7065025750994682, |
| "eval_math_loss": 0.8846055865287781, |
| "eval_math_mean_token_accuracy": 0.7727578555345536, |
| "eval_math_num_tokens": 11299223.0, |
| "eval_math_runtime": 42.3209, |
| "eval_math_samples_per_second": 11.814, |
| "eval_math_steps_per_second": 11.814, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.7566905914427197, |
| "eval_physics_entropy": 0.7156323294043541, |
| "eval_physics_loss": 0.7419880628585815, |
| "eval_physics_mean_token_accuracy": 0.794500320136547, |
| "eval_physics_num_tokens": 11299223.0, |
| "eval_physics_runtime": 46.3513, |
| "eval_physics_samples_per_second": 10.787, |
| "eval_physics_steps_per_second": 10.787, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.6807379337958992, |
| "epoch": 0.7611417125688533, |
| "grad_norm": 44.5, |
| "learning_rate": 1.842444444444445e-05, |
| "loss": 10.903, |
| "mean_token_accuracy": 0.806118119508028, |
| "num_tokens": 11371200.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 0.6858457752503455, |
| "epoch": 0.7655928336949869, |
| "grad_norm": 48.5, |
| "learning_rate": 1.8402222222222223e-05, |
| "loss": 11.2529, |
| "mean_token_accuracy": 0.8003716830164194, |
| "num_tokens": 11436799.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 0.6833723585121334, |
| "epoch": 0.7700439548211205, |
| "grad_norm": 56.25, |
| "learning_rate": 1.8380000000000004e-05, |
| "loss": 10.8605, |
| "mean_token_accuracy": 0.8072644464671612, |
| "num_tokens": 11502965.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 0.7146074397489428, |
| "epoch": 0.7744950759472542, |
| "grad_norm": 46.5, |
| "learning_rate": 1.8357777777777778e-05, |
| "loss": 11.5601, |
| "mean_token_accuracy": 0.7982227748259902, |
| "num_tokens": 11567422.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 0.6696322374045849, |
| "epoch": 0.7789461970733879, |
| "grad_norm": 38.5, |
| "learning_rate": 1.833555555555556e-05, |
| "loss": 10.8469, |
| "mean_token_accuracy": 0.8079163532704114, |
| "num_tokens": 11637076.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.7314721707254648, |
| "epoch": 0.7833973181995215, |
| "grad_norm": 50.0, |
| "learning_rate": 1.8313333333333333e-05, |
| "loss": 11.7653, |
| "mean_token_accuracy": 0.7910329852253198, |
| "num_tokens": 11703496.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 0.645071561448276, |
| "epoch": 0.7878484393256552, |
| "grad_norm": 36.75, |
| "learning_rate": 1.8291111111111114e-05, |
| "loss": 10.1798, |
| "mean_token_accuracy": 0.8178190600126982, |
| "num_tokens": 11772773.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 0.656541757658124, |
| "epoch": 0.7922995604517888, |
| "grad_norm": 46.75, |
| "learning_rate": 1.8268888888888888e-05, |
| "loss": 10.7678, |
| "mean_token_accuracy": 0.8082757320255041, |
| "num_tokens": 11840317.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 0.7429797733202577, |
| "epoch": 0.7967506815779224, |
| "grad_norm": 59.75, |
| "learning_rate": 1.824666666666667e-05, |
| "loss": 11.9596, |
| "mean_token_accuracy": 0.7920549724251031, |
| "num_tokens": 11903376.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 0.6890028819441796, |
| "epoch": 0.801201802704056, |
| "grad_norm": 52.0, |
| "learning_rate": 1.8224444444444447e-05, |
| "loss": 10.9936, |
| "mean_token_accuracy": 0.8042987301945687, |
| "num_tokens": 11965530.0, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.801201802704056, |
| "eval_biology_entropy": 1.277042101919651, |
| "eval_biology_loss": 1.332998275756836, |
| "eval_biology_mean_token_accuracy": 0.6726464540362358, |
| "eval_biology_num_tokens": 11965530.0, |
| "eval_biology_runtime": 37.3225, |
| "eval_biology_samples_per_second": 13.397, |
| "eval_biology_steps_per_second": 13.397, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.801201802704056, |
| "eval_chemistry_entropy": 0.6964197388291359, |
| "eval_chemistry_loss": 0.6977025270462036, |
| "eval_chemistry_mean_token_accuracy": 0.800601690530777, |
| "eval_chemistry_num_tokens": 11965530.0, |
| "eval_chemistry_runtime": 41.1955, |
| "eval_chemistry_samples_per_second": 12.137, |
| "eval_chemistry_steps_per_second": 12.137, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.801201802704056, |
| "eval_math_entropy": 0.691622546583414, |
| "eval_math_loss": 0.884013831615448, |
| "eval_math_mean_token_accuracy": 0.7728146443367004, |
| "eval_math_num_tokens": 11965530.0, |
| "eval_math_runtime": 41.3293, |
| "eval_math_samples_per_second": 12.098, |
| "eval_math_steps_per_second": 12.098, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.801201802704056, |
| "eval_physics_entropy": 0.7113458831310272, |
| "eval_physics_loss": 0.7380439639091492, |
| "eval_physics_mean_token_accuracy": 0.7949880036711693, |
| "eval_physics_num_tokens": 11965530.0, |
| "eval_physics_runtime": 45.7175, |
| "eval_physics_samples_per_second": 10.937, |
| "eval_physics_steps_per_second": 10.937, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.6916238307952881, |
| "epoch": 0.8056529238301897, |
| "grad_norm": 54.0, |
| "learning_rate": 1.8202222222222225e-05, |
| "loss": 11.1738, |
| "mean_token_accuracy": 0.802581525221467, |
| "num_tokens": 12031493.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 0.6883499003015459, |
| "epoch": 0.8101040449563234, |
| "grad_norm": 47.0, |
| "learning_rate": 1.8180000000000002e-05, |
| "loss": 11.1564, |
| "mean_token_accuracy": 0.8044124312698842, |
| "num_tokens": 12097917.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 0.6930434329435229, |
| "epoch": 0.814555166082457, |
| "grad_norm": 46.25, |
| "learning_rate": 1.815777777777778e-05, |
| "loss": 11.0779, |
| "mean_token_accuracy": 0.8034347232431174, |
| "num_tokens": 12163029.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 0.6947093228809536, |
| "epoch": 0.8190062872085907, |
| "grad_norm": 58.5, |
| "learning_rate": 1.8135555555555557e-05, |
| "loss": 11.3123, |
| "mean_token_accuracy": 0.7996832799166441, |
| "num_tokens": 12224427.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 0.719798219576478, |
| "epoch": 0.8234574083347244, |
| "grad_norm": 43.25, |
| "learning_rate": 1.8113333333333335e-05, |
| "loss": 11.4131, |
| "mean_token_accuracy": 0.8016381539404392, |
| "num_tokens": 12291917.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 0.669582040514797, |
| "epoch": 0.8279085294608579, |
| "grad_norm": 48.25, |
| "learning_rate": 1.8091111111111113e-05, |
| "loss": 10.7576, |
| "mean_token_accuracy": 0.8064643792808056, |
| "num_tokens": 12365332.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 0.6633579313755036, |
| "epoch": 0.8323596505869916, |
| "grad_norm": 41.25, |
| "learning_rate": 1.806888888888889e-05, |
| "loss": 10.6729, |
| "mean_token_accuracy": 0.806138664111495, |
| "num_tokens": 12441423.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 0.6549396699294447, |
| "epoch": 0.8368107717131252, |
| "grad_norm": 50.5, |
| "learning_rate": 1.8046666666666668e-05, |
| "loss": 10.4457, |
| "mean_token_accuracy": 0.8124689020216465, |
| "num_tokens": 12509124.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 0.6255366197787225, |
| "epoch": 0.8412618928392589, |
| "grad_norm": 43.25, |
| "learning_rate": 1.8024444444444445e-05, |
| "loss": 10.236, |
| "mean_token_accuracy": 0.8123138222843409, |
| "num_tokens": 12575355.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 0.6981251872144639, |
| "epoch": 0.8457130139653926, |
| "grad_norm": 59.75, |
| "learning_rate": 1.8002222222222223e-05, |
| "loss": 11.3401, |
| "mean_token_accuracy": 0.799917110055685, |
| "num_tokens": 12642651.0, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.8457130139653926, |
| "eval_biology_entropy": 1.2781688437461853, |
| "eval_biology_loss": 1.337692379951477, |
| "eval_biology_mean_token_accuracy": 0.6727457674741745, |
| "eval_biology_num_tokens": 12642651.0, |
| "eval_biology_runtime": 36.7254, |
| "eval_biology_samples_per_second": 13.615, |
| "eval_biology_steps_per_second": 13.615, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.8457130139653926, |
| "eval_chemistry_entropy": 0.6981815086901187, |
| "eval_chemistry_loss": 0.6955837607383728, |
| "eval_chemistry_mean_token_accuracy": 0.8022230199575424, |
| "eval_chemistry_num_tokens": 12642651.0, |
| "eval_chemistry_runtime": 40.4028, |
| "eval_chemistry_samples_per_second": 12.375, |
| "eval_chemistry_steps_per_second": 12.375, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.8457130139653926, |
| "eval_math_entropy": 0.6860641204416752, |
| "eval_math_loss": 0.8941249251365662, |
| "eval_math_mean_token_accuracy": 0.7716994079351425, |
| "eval_math_num_tokens": 12642651.0, |
| "eval_math_runtime": 41.4747, |
| "eval_math_samples_per_second": 12.056, |
| "eval_math_steps_per_second": 12.056, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.8457130139653926, |
| "eval_physics_entropy": 0.7120301985144615, |
| "eval_physics_loss": 0.7369678020477295, |
| "eval_physics_mean_token_accuracy": 0.7946544420719147, |
| "eval_physics_num_tokens": 12642651.0, |
| "eval_physics_runtime": 45.5815, |
| "eval_physics_samples_per_second": 10.969, |
| "eval_physics_steps_per_second": 10.969, |
| "step": 1900 |
| }, |
| { |
| "entropy": 0.6538136603310705, |
| "epoch": 0.8501641350915262, |
| "grad_norm": 42.0, |
| "learning_rate": 1.798e-05, |
| "loss": 10.2863, |
| "mean_token_accuracy": 0.8125439338386059, |
| "num_tokens": 12710065.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 0.6856445983983577, |
| "epoch": 0.8546152562176598, |
| "grad_norm": 50.75, |
| "learning_rate": 1.7957777777777778e-05, |
| "loss": 10.9931, |
| "mean_token_accuracy": 0.8032558988779783, |
| "num_tokens": 12778408.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 0.6402218439616263, |
| "epoch": 0.8590663773437934, |
| "grad_norm": 53.75, |
| "learning_rate": 1.7935555555555556e-05, |
| "loss": 10.3931, |
| "mean_token_accuracy": 0.8133255753666162, |
| "num_tokens": 12845949.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 0.687981967907399, |
| "epoch": 0.8635174984699271, |
| "grad_norm": 53.5, |
| "learning_rate": 1.7913333333333337e-05, |
| "loss": 10.9298, |
| "mean_token_accuracy": 0.8087461933493614, |
| "num_tokens": 12910630.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 0.6755717716179788, |
| "epoch": 0.8679686195960608, |
| "grad_norm": 47.75, |
| "learning_rate": 1.789111111111111e-05, |
| "loss": 11.1314, |
| "mean_token_accuracy": 0.8019361585378647, |
| "num_tokens": 12975379.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 0.6678634139709174, |
| "epoch": 0.8724197407221944, |
| "grad_norm": 42.0, |
| "learning_rate": 1.7868888888888892e-05, |
| "loss": 10.5302, |
| "mean_token_accuracy": 0.8089069448411464, |
| "num_tokens": 13046473.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 0.7141758069396019, |
| "epoch": 0.8768708618483281, |
| "grad_norm": 44.75, |
| "learning_rate": 1.7846666666666666e-05, |
| "loss": 11.6782, |
| "mean_token_accuracy": 0.7963042937219142, |
| "num_tokens": 13105019.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 0.7312607789412141, |
| "epoch": 0.8813219829744617, |
| "grad_norm": 47.75, |
| "learning_rate": 1.7824444444444447e-05, |
| "loss": 11.4252, |
| "mean_token_accuracy": 0.8010873660445214, |
| "num_tokens": 13167768.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 0.6517805024050176, |
| "epoch": 0.8857731041005953, |
| "grad_norm": 46.25, |
| "learning_rate": 1.780222222222222e-05, |
| "loss": 10.6298, |
| "mean_token_accuracy": 0.8119962867349386, |
| "num_tokens": 13235899.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 0.6774258488789201, |
| "epoch": 0.890224225226729, |
| "grad_norm": 40.5, |
| "learning_rate": 1.7780000000000003e-05, |
| "loss": 10.7589, |
| "mean_token_accuracy": 0.8065350767225027, |
| "num_tokens": 13301659.0, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.890224225226729, |
| "eval_biology_entropy": 1.2670730832815171, |
| "eval_biology_loss": 1.333166241645813, |
| "eval_biology_mean_token_accuracy": 0.6740682775974274, |
| "eval_biology_num_tokens": 13301659.0, |
| "eval_biology_runtime": 36.6935, |
| "eval_biology_samples_per_second": 13.626, |
| "eval_biology_steps_per_second": 13.626, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.890224225226729, |
| "eval_chemistry_entropy": 0.6871010038554668, |
| "eval_chemistry_loss": 0.6869096755981445, |
| "eval_chemistry_mean_token_accuracy": 0.8039456156492233, |
| "eval_chemistry_num_tokens": 13301659.0, |
| "eval_chemistry_runtime": 40.6168, |
| "eval_chemistry_samples_per_second": 12.31, |
| "eval_chemistry_steps_per_second": 12.31, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.890224225226729, |
| "eval_math_entropy": 0.6870918811559678, |
| "eval_math_loss": 0.8818830847740173, |
| "eval_math_mean_token_accuracy": 0.7737292177677154, |
| "eval_math_num_tokens": 13301659.0, |
| "eval_math_runtime": 41.1765, |
| "eval_math_samples_per_second": 12.143, |
| "eval_math_steps_per_second": 12.143, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.890224225226729, |
| "eval_physics_entropy": 0.7050596924424172, |
| "eval_physics_loss": 0.7348896861076355, |
| "eval_physics_mean_token_accuracy": 0.7955606966018677, |
| "eval_physics_num_tokens": 13301659.0, |
| "eval_physics_runtime": 45.6515, |
| "eval_physics_samples_per_second": 10.953, |
| "eval_physics_steps_per_second": 10.953, |
| "step": 2000 |
| }, |
| { |
| "entropy": 0.6624653632752597, |
| "epoch": 0.8946753463528626, |
| "grad_norm": 47.25, |
| "learning_rate": 1.7757777777777777e-05, |
| "loss": 10.6738, |
| "mean_token_accuracy": 0.809033065661788, |
| "num_tokens": 13368880.0, |
| "step": 2010 |
| }, |
| { |
| "entropy": 0.7088313958607614, |
| "epoch": 0.8991264674789963, |
| "grad_norm": 51.25, |
| "learning_rate": 1.7735555555555558e-05, |
| "loss": 11.251, |
| "mean_token_accuracy": 0.8030012097209692, |
| "num_tokens": 13434364.0, |
| "step": 2020 |
| }, |
| { |
| "entropy": 0.6664689189754427, |
| "epoch": 0.9035775886051299, |
| "grad_norm": 47.75, |
| "learning_rate": 1.7713333333333335e-05, |
| "loss": 10.8209, |
| "mean_token_accuracy": 0.809228365495801, |
| "num_tokens": 13499871.0, |
| "step": 2030 |
| }, |
| { |
| "entropy": 0.6379630077630282, |
| "epoch": 0.9080287097312636, |
| "grad_norm": 41.25, |
| "learning_rate": 1.7691111111111113e-05, |
| "loss": 10.2334, |
| "mean_token_accuracy": 0.817959938570857, |
| "num_tokens": 13570986.0, |
| "step": 2040 |
| }, |
| { |
| "entropy": 0.602727087866515, |
| "epoch": 0.9124798308573973, |
| "grad_norm": 43.0, |
| "learning_rate": 1.766888888888889e-05, |
| "loss": 9.6466, |
| "mean_token_accuracy": 0.8242635581642389, |
| "num_tokens": 13639400.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 0.7078336867503822, |
| "epoch": 0.9169309519835308, |
| "grad_norm": 43.25, |
| "learning_rate": 1.7646666666666668e-05, |
| "loss": 11.4415, |
| "mean_token_accuracy": 0.8023648094385862, |
| "num_tokens": 13706343.0, |
| "step": 2060 |
| }, |
| { |
| "entropy": 0.7338959392160177, |
| "epoch": 0.9213820731096645, |
| "grad_norm": 50.75, |
| "learning_rate": 1.7624444444444446e-05, |
| "loss": 11.7122, |
| "mean_token_accuracy": 0.795870553702116, |
| "num_tokens": 13772145.0, |
| "step": 2070 |
| }, |
| { |
| "entropy": 0.6916357525624335, |
| "epoch": 0.9258331942357981, |
| "grad_norm": 46.5, |
| "learning_rate": 1.7602222222222223e-05, |
| "loss": 11.2013, |
| "mean_token_accuracy": 0.804204386100173, |
| "num_tokens": 13833901.0, |
| "step": 2080 |
| }, |
| { |
| "entropy": 0.692809761222452, |
| "epoch": 0.9302843153619318, |
| "grad_norm": 56.25, |
| "learning_rate": 1.758e-05, |
| "loss": 11.0936, |
| "mean_token_accuracy": 0.8052353203296662, |
| "num_tokens": 13890922.0, |
| "step": 2090 |
| }, |
| { |
| "entropy": 0.6622355343773961, |
| "epoch": 0.9347354364880655, |
| "grad_norm": 49.25, |
| "learning_rate": 1.755777777777778e-05, |
| "loss": 10.7104, |
| "mean_token_accuracy": 0.806670430675149, |
| "num_tokens": 13954258.0, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.9347354364880655, |
| "eval_biology_entropy": 1.2462336373329164, |
| "eval_biology_loss": 1.3325841426849365, |
| "eval_biology_mean_token_accuracy": 0.6730192624926568, |
| "eval_biology_num_tokens": 13954258.0, |
| "eval_biology_runtime": 37.5397, |
| "eval_biology_samples_per_second": 13.319, |
| "eval_biology_steps_per_second": 13.319, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.9347354364880655, |
| "eval_chemistry_entropy": 0.6734770992100239, |
| "eval_chemistry_loss": 0.6857835054397583, |
| "eval_chemistry_mean_token_accuracy": 0.8044139510393142, |
| "eval_chemistry_num_tokens": 13954258.0, |
| "eval_chemistry_runtime": 41.0842, |
| "eval_chemistry_samples_per_second": 12.17, |
| "eval_chemistry_steps_per_second": 12.17, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.9347354364880655, |
| "eval_math_entropy": 0.690498467206955, |
| "eval_math_loss": 0.879159688949585, |
| "eval_math_mean_token_accuracy": 0.774110961675644, |
| "eval_math_num_tokens": 13954258.0, |
| "eval_math_runtime": 41.6262, |
| "eval_math_samples_per_second": 12.012, |
| "eval_math_steps_per_second": 12.012, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.9347354364880655, |
| "eval_physics_entropy": 0.7076400628387928, |
| "eval_physics_loss": 0.7340090274810791, |
| "eval_physics_mean_token_accuracy": 0.7960616961717606, |
| "eval_physics_num_tokens": 13954258.0, |
| "eval_physics_runtime": 45.6092, |
| "eval_physics_samples_per_second": 10.963, |
| "eval_physics_steps_per_second": 10.963, |
| "step": 2100 |
| }, |
| { |
| "entropy": 0.6589104058220983, |
| "epoch": 0.9391865576141991, |
| "grad_norm": 47.0, |
| "learning_rate": 1.7535555555555556e-05, |
| "loss": 10.3503, |
| "mean_token_accuracy": 0.8144653994590044, |
| "num_tokens": 14024422.0, |
| "step": 2110 |
| }, |
| { |
| "entropy": 0.6486032720655203, |
| "epoch": 0.9436376787403328, |
| "grad_norm": 53.5, |
| "learning_rate": 1.7513333333333334e-05, |
| "loss": 10.4779, |
| "mean_token_accuracy": 0.8101291112601757, |
| "num_tokens": 14093888.0, |
| "step": 2120 |
| }, |
| { |
| "entropy": 0.6803323580883444, |
| "epoch": 0.9480887998664663, |
| "grad_norm": 48.75, |
| "learning_rate": 1.749111111111111e-05, |
| "loss": 10.9885, |
| "mean_token_accuracy": 0.80365344658494, |
| "num_tokens": 14160983.0, |
| "step": 2130 |
| }, |
| { |
| "entropy": 0.6727567315101624, |
| "epoch": 0.9525399209926, |
| "grad_norm": 51.25, |
| "learning_rate": 1.746888888888889e-05, |
| "loss": 10.7152, |
| "mean_token_accuracy": 0.8089216817170382, |
| "num_tokens": 14222626.0, |
| "step": 2140 |
| }, |
| { |
| "entropy": 0.6865859323181212, |
| "epoch": 0.9569910421187336, |
| "grad_norm": 45.75, |
| "learning_rate": 1.7446666666666667e-05, |
| "loss": 11.0247, |
| "mean_token_accuracy": 0.8013521831482648, |
| "num_tokens": 14287730.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 0.6925968321040272, |
| "epoch": 0.9614421632448673, |
| "grad_norm": 50.25, |
| "learning_rate": 1.7424444444444444e-05, |
| "loss": 11.0458, |
| "mean_token_accuracy": 0.8054416980594397, |
| "num_tokens": 14354918.0, |
| "step": 2160 |
| }, |
| { |
| "entropy": 0.6530994305387139, |
| "epoch": 0.965893284371001, |
| "grad_norm": 54.75, |
| "learning_rate": 1.7402222222222222e-05, |
| "loss": 10.5897, |
| "mean_token_accuracy": 0.8102857951074839, |
| "num_tokens": 14427338.0, |
| "step": 2170 |
| }, |
| { |
| "entropy": 0.6711476687341928, |
| "epoch": 0.9703444054971346, |
| "grad_norm": 44.25, |
| "learning_rate": 1.7380000000000003e-05, |
| "loss": 10.7937, |
| "mean_token_accuracy": 0.8047963213175535, |
| "num_tokens": 14493349.0, |
| "step": 2180 |
| }, |
| { |
| "entropy": 0.6828335174359381, |
| "epoch": 0.9747955266232682, |
| "grad_norm": 46.25, |
| "learning_rate": 1.735777777777778e-05, |
| "loss": 10.8038, |
| "mean_token_accuracy": 0.8060759626328945, |
| "num_tokens": 14555091.0, |
| "step": 2190 |
| }, |
| { |
| "entropy": 0.6434482355602086, |
| "epoch": 0.9792466477494018, |
| "grad_norm": 44.75, |
| "learning_rate": 1.7335555555555558e-05, |
| "loss": 10.2743, |
| "mean_token_accuracy": 0.8180668748915195, |
| "num_tokens": 14620244.0, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.9792466477494018, |
| "eval_biology_entropy": 1.247750738620758, |
| "eval_biology_loss": 1.3323266506195068, |
| "eval_biology_mean_token_accuracy": 0.6733877260684967, |
| "eval_biology_num_tokens": 14620244.0, |
| "eval_biology_runtime": 36.9535, |
| "eval_biology_samples_per_second": 13.531, |
| "eval_biology_steps_per_second": 13.531, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.9792466477494018, |
| "eval_chemistry_entropy": 0.6709461865127087, |
| "eval_chemistry_loss": 0.6788121461868286, |
| "eval_chemistry_mean_token_accuracy": 0.8056401910781861, |
| "eval_chemistry_num_tokens": 14620244.0, |
| "eval_chemistry_runtime": 40.4431, |
| "eval_chemistry_samples_per_second": 12.363, |
| "eval_chemistry_steps_per_second": 12.363, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.9792466477494018, |
| "eval_math_entropy": 0.6754355610609054, |
| "eval_math_loss": 0.8837116956710815, |
| "eval_math_mean_token_accuracy": 0.7731442128419876, |
| "eval_math_num_tokens": 14620244.0, |
| "eval_math_runtime": 41.713, |
| "eval_math_samples_per_second": 11.987, |
| "eval_math_steps_per_second": 11.987, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.9792466477494018, |
| "eval_physics_entropy": 0.7011642599105835, |
| "eval_physics_loss": 0.7309737801551819, |
| "eval_physics_mean_token_accuracy": 0.7966242255568504, |
| "eval_physics_num_tokens": 14620244.0, |
| "eval_physics_runtime": 45.581, |
| "eval_physics_samples_per_second": 10.969, |
| "eval_physics_steps_per_second": 10.969, |
| "step": 2200 |
| }, |
| { |
| "entropy": 0.6384785600006581, |
| "epoch": 0.9836977688755355, |
| "grad_norm": 43.25, |
| "learning_rate": 1.7313333333333336e-05, |
| "loss": 10.2457, |
| "mean_token_accuracy": 0.8158678378909826, |
| "num_tokens": 14688111.0, |
| "step": 2210 |
| }, |
| { |
| "entropy": 0.6514905813150108, |
| "epoch": 0.9881488900016692, |
| "grad_norm": 41.25, |
| "learning_rate": 1.7291111111111113e-05, |
| "loss": 10.3912, |
| "mean_token_accuracy": 0.813620499521494, |
| "num_tokens": 14760951.0, |
| "step": 2220 |
| }, |
| { |
| "entropy": 0.7030717304907739, |
| "epoch": 0.9926000111278028, |
| "grad_norm": 46.25, |
| "learning_rate": 1.726888888888889e-05, |
| "loss": 11.3263, |
| "mean_token_accuracy": 0.8024369370192289, |
| "num_tokens": 14823141.0, |
| "step": 2230 |
| }, |
| { |
| "entropy": 0.6680187570862473, |
| "epoch": 0.9970511322539365, |
| "grad_norm": 46.5, |
| "learning_rate": 1.724666666666667e-05, |
| "loss": 10.7516, |
| "mean_token_accuracy": 0.8081471104174852, |
| "num_tokens": 14886593.0, |
| "step": 2240 |
| }, |
| { |
| "entropy": 0.6284090471151588, |
| "epoch": 1.00133533633784, |
| "grad_norm": 45.0, |
| "learning_rate": 1.7224444444444446e-05, |
| "loss": 9.2827, |
| "mean_token_accuracy": 0.8244597559625452, |
| "num_tokens": 14951602.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 0.4474197247996926, |
| "epoch": 1.0057864574639737, |
| "grad_norm": 48.0, |
| "learning_rate": 1.7202222222222224e-05, |
| "loss": 7.2757, |
| "mean_token_accuracy": 0.8661276008933783, |
| "num_tokens": 15016941.0, |
| "step": 2260 |
| }, |
| { |
| "entropy": 0.4514174465090036, |
| "epoch": 1.0102375785901074, |
| "grad_norm": 46.5, |
| "learning_rate": 1.718e-05, |
| "loss": 7.1492, |
| "mean_token_accuracy": 0.8681086041033268, |
| "num_tokens": 15083858.0, |
| "step": 2270 |
| }, |
| { |
| "entropy": 0.42378407744690777, |
| "epoch": 1.014688699716241, |
| "grad_norm": 43.0, |
| "learning_rate": 1.715777777777778e-05, |
| "loss": 6.6083, |
| "mean_token_accuracy": 0.8740248043090105, |
| "num_tokens": 15152865.0, |
| "step": 2280 |
| }, |
| { |
| "entropy": 0.43617964098230005, |
| "epoch": 1.0191398208423748, |
| "grad_norm": 47.0, |
| "learning_rate": 1.7135555555555557e-05, |
| "loss": 7.125, |
| "mean_token_accuracy": 0.8656272307038307, |
| "num_tokens": 15218564.0, |
| "step": 2290 |
| }, |
| { |
| "entropy": 0.46345840478315947, |
| "epoch": 1.0235909419685083, |
| "grad_norm": 52.75, |
| "learning_rate": 1.7113333333333334e-05, |
| "loss": 7.2499, |
| "mean_token_accuracy": 0.864538699388504, |
| "num_tokens": 15281217.0, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.0235909419685083, |
| "eval_biology_entropy": 1.0195375851392745, |
| "eval_biology_loss": 1.3763028383255005, |
| "eval_biology_mean_token_accuracy": 0.6724755849838256, |
| "eval_biology_num_tokens": 15281217.0, |
| "eval_biology_runtime": 36.8395, |
| "eval_biology_samples_per_second": 13.572, |
| "eval_biology_steps_per_second": 13.572, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.0235909419685083, |
| "eval_chemistry_entropy": 0.54003151974082, |
| "eval_chemistry_loss": 0.6988040804862976, |
| "eval_chemistry_mean_token_accuracy": 0.8042957043647766, |
| "eval_chemistry_num_tokens": 15281217.0, |
| "eval_chemistry_runtime": 40.271, |
| "eval_chemistry_samples_per_second": 12.416, |
| "eval_chemistry_steps_per_second": 12.416, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.0235909419685083, |
| "eval_math_entropy": 0.6100949879586697, |
| "eval_math_loss": 0.8924350142478943, |
| "eval_math_mean_token_accuracy": 0.7739938046932221, |
| "eval_math_num_tokens": 15281217.0, |
| "eval_math_runtime": 41.9005, |
| "eval_math_samples_per_second": 11.933, |
| "eval_math_steps_per_second": 11.933, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.0235909419685083, |
| "eval_physics_entropy": 0.5909477268755436, |
| "eval_physics_loss": 0.7466819882392883, |
| "eval_physics_mean_token_accuracy": 0.7956570327281952, |
| "eval_physics_num_tokens": 15281217.0, |
| "eval_physics_runtime": 45.5138, |
| "eval_physics_samples_per_second": 10.986, |
| "eval_physics_steps_per_second": 10.986, |
| "step": 2300 |
| }, |
| { |
| "entropy": 0.4489840595982969, |
| "epoch": 1.0280420630946419, |
| "grad_norm": 42.25, |
| "learning_rate": 1.7091111111111112e-05, |
| "loss": 7.2226, |
| "mean_token_accuracy": 0.8643945761024951, |
| "num_tokens": 15346128.0, |
| "step": 2310 |
| }, |
| { |
| "entropy": 0.4520178667269647, |
| "epoch": 1.0324931842207756, |
| "grad_norm": 40.5, |
| "learning_rate": 1.706888888888889e-05, |
| "loss": 7.4866, |
| "mean_token_accuracy": 0.8607839841395617, |
| "num_tokens": 15412606.0, |
| "step": 2320 |
| }, |
| { |
| "entropy": 0.4522146672010422, |
| "epoch": 1.0369443053469092, |
| "grad_norm": 48.0, |
| "learning_rate": 1.704666666666667e-05, |
| "loss": 7.011, |
| "mean_token_accuracy": 0.8670971356332302, |
| "num_tokens": 15484636.0, |
| "step": 2330 |
| }, |
| { |
| "entropy": 0.41863614730536935, |
| "epoch": 1.041395426473043, |
| "grad_norm": 50.25, |
| "learning_rate": 1.7024444444444445e-05, |
| "loss": 6.6836, |
| "mean_token_accuracy": 0.8738284990191459, |
| "num_tokens": 15556398.0, |
| "step": 2340 |
| }, |
| { |
| "entropy": 0.4294653506949544, |
| "epoch": 1.0458465475991765, |
| "grad_norm": 62.0, |
| "learning_rate": 1.7002222222222226e-05, |
| "loss": 6.9672, |
| "mean_token_accuracy": 0.8710181381553411, |
| "num_tokens": 15624248.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 0.466453810967505, |
| "epoch": 1.0502976687253103, |
| "grad_norm": 44.5, |
| "learning_rate": 1.698e-05, |
| "loss": 7.3633, |
| "mean_token_accuracy": 0.8629629045724869, |
| "num_tokens": 15689184.0, |
| "step": 2360 |
| }, |
| { |
| "entropy": 0.4625964089296758, |
| "epoch": 1.0547487898514438, |
| "grad_norm": 55.75, |
| "learning_rate": 1.695777777777778e-05, |
| "loss": 7.4865, |
| "mean_token_accuracy": 0.860261058434844, |
| "num_tokens": 15754370.0, |
| "step": 2370 |
| }, |
| { |
| "entropy": 0.4521440314128995, |
| "epoch": 1.0591999109775774, |
| "grad_norm": 42.0, |
| "learning_rate": 1.6935555555555555e-05, |
| "loss": 7.1616, |
| "mean_token_accuracy": 0.865738482773304, |
| "num_tokens": 15824975.0, |
| "step": 2380 |
| }, |
| { |
| "entropy": 0.4556281536817551, |
| "epoch": 1.0636510321037111, |
| "grad_norm": 48.25, |
| "learning_rate": 1.6913333333333336e-05, |
| "loss": 7.3322, |
| "mean_token_accuracy": 0.8630469419062138, |
| "num_tokens": 15886149.0, |
| "step": 2390 |
| }, |
| { |
| "entropy": 0.4443885440006852, |
| "epoch": 1.0681021532298447, |
| "grad_norm": 43.75, |
| "learning_rate": 1.689111111111111e-05, |
| "loss": 7.142, |
| "mean_token_accuracy": 0.8662454362958669, |
| "num_tokens": 15956560.0, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.0681021532298447, |
| "eval_biology_entropy": 1.085576331436634, |
| "eval_biology_loss": 1.3607929944992065, |
| "eval_biology_mean_token_accuracy": 0.6722971173524857, |
| "eval_biology_num_tokens": 15956560.0, |
| "eval_biology_runtime": 36.2114, |
| "eval_biology_samples_per_second": 13.808, |
| "eval_biology_steps_per_second": 13.808, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.0681021532298447, |
| "eval_chemistry_entropy": 0.573589419811964, |
| "eval_chemistry_loss": 0.6865324974060059, |
| "eval_chemistry_mean_token_accuracy": 0.8060856524705887, |
| "eval_chemistry_num_tokens": 15956560.0, |
| "eval_chemistry_runtime": 40.7118, |
| "eval_chemistry_samples_per_second": 12.281, |
| "eval_chemistry_steps_per_second": 12.281, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.0681021532298447, |
| "eval_math_entropy": 0.6420403882265091, |
| "eval_math_loss": 0.8827968239784241, |
| "eval_math_mean_token_accuracy": 0.7741341978311539, |
| "eval_math_num_tokens": 15956560.0, |
| "eval_math_runtime": 41.0351, |
| "eval_math_samples_per_second": 12.185, |
| "eval_math_steps_per_second": 12.185, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.0681021532298447, |
| "eval_physics_entropy": 0.6184939668476581, |
| "eval_physics_loss": 0.7397767305374146, |
| "eval_physics_mean_token_accuracy": 0.7973104780316352, |
| "eval_physics_num_tokens": 15956560.0, |
| "eval_physics_runtime": 45.728, |
| "eval_physics_samples_per_second": 10.934, |
| "eval_physics_steps_per_second": 10.934, |
| "step": 2400 |
| }, |
| { |
| "entropy": 0.46900504967197776, |
| "epoch": 1.0725532743559785, |
| "grad_norm": 45.0, |
| "learning_rate": 1.686888888888889e-05, |
| "loss": 7.4466, |
| "mean_token_accuracy": 0.8614247545599938, |
| "num_tokens": 16025633.0, |
| "step": 2410 |
| }, |
| { |
| "entropy": 0.44829527800902724, |
| "epoch": 1.077004395482112, |
| "grad_norm": 57.25, |
| "learning_rate": 1.684666666666667e-05, |
| "loss": 7.1649, |
| "mean_token_accuracy": 0.8657123044133186, |
| "num_tokens": 16094535.0, |
| "step": 2420 |
| }, |
| { |
| "entropy": 0.4610415279865265, |
| "epoch": 1.0814555166082458, |
| "grad_norm": 50.75, |
| "learning_rate": 1.6824444444444447e-05, |
| "loss": 7.349, |
| "mean_token_accuracy": 0.8612112984061241, |
| "num_tokens": 16159781.0, |
| "step": 2430 |
| }, |
| { |
| "entropy": 0.4499107955023646, |
| "epoch": 1.0859066377343793, |
| "grad_norm": 45.5, |
| "learning_rate": 1.6802222222222224e-05, |
| "loss": 7.1851, |
| "mean_token_accuracy": 0.865880173817277, |
| "num_tokens": 16227695.0, |
| "step": 2440 |
| }, |
| { |
| "entropy": 0.4479747975245118, |
| "epoch": 1.090357758860513, |
| "grad_norm": 58.25, |
| "learning_rate": 1.6780000000000002e-05, |
| "loss": 7.1191, |
| "mean_token_accuracy": 0.8650641094893217, |
| "num_tokens": 16293211.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 0.4491896514315158, |
| "epoch": 1.0948088799866467, |
| "grad_norm": 48.5, |
| "learning_rate": 1.675777777777778e-05, |
| "loss": 7.0793, |
| "mean_token_accuracy": 0.8705599319189787, |
| "num_tokens": 16361111.0, |
| "step": 2460 |
| }, |
| { |
| "entropy": 0.466768235899508, |
| "epoch": 1.0992600011127802, |
| "grad_norm": 43.75, |
| "learning_rate": 1.6735555555555557e-05, |
| "loss": 7.4591, |
| "mean_token_accuracy": 0.8619610998779536, |
| "num_tokens": 16424587.0, |
| "step": 2470 |
| }, |
| { |
| "entropy": 0.4429409301839769, |
| "epoch": 1.103711122238914, |
| "grad_norm": 37.5, |
| "learning_rate": 1.6713333333333335e-05, |
| "loss": 7.1464, |
| "mean_token_accuracy": 0.8677466906607151, |
| "num_tokens": 16495082.0, |
| "step": 2480 |
| }, |
| { |
| "entropy": 0.43836286664009094, |
| "epoch": 1.1081622433650475, |
| "grad_norm": 55.0, |
| "learning_rate": 1.6691111111111112e-05, |
| "loss": 7.0627, |
| "mean_token_accuracy": 0.8674808170646429, |
| "num_tokens": 16557596.0, |
| "step": 2490 |
| }, |
| { |
| "entropy": 0.4672828443348408, |
| "epoch": 1.1126133644911813, |
| "grad_norm": 40.75, |
| "learning_rate": 1.666888888888889e-05, |
| "loss": 7.2798, |
| "mean_token_accuracy": 0.8640754166990519, |
| "num_tokens": 16625999.0, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.1126133644911813, |
| "eval_biology_entropy": 1.0831511808633805, |
| "eval_biology_loss": 1.3569880723953247, |
| "eval_biology_mean_token_accuracy": 0.6740138655304909, |
| "eval_biology_num_tokens": 16625999.0, |
| "eval_biology_runtime": 36.9597, |
| "eval_biology_samples_per_second": 13.528, |
| "eval_biology_steps_per_second": 13.528, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.1126133644911813, |
| "eval_chemistry_entropy": 0.58320310485363, |
| "eval_chemistry_loss": 0.6820600628852844, |
| "eval_chemistry_mean_token_accuracy": 0.8071107329130173, |
| "eval_chemistry_num_tokens": 16625999.0, |
| "eval_chemistry_runtime": 40.3591, |
| "eval_chemistry_samples_per_second": 12.389, |
| "eval_chemistry_steps_per_second": 12.389, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.1126133644911813, |
| "eval_math_entropy": 0.6613843004703521, |
| "eval_math_loss": 0.8857272267341614, |
| "eval_math_mean_token_accuracy": 0.7728515480756759, |
| "eval_math_num_tokens": 16625999.0, |
| "eval_math_runtime": 40.9092, |
| "eval_math_samples_per_second": 12.222, |
| "eval_math_steps_per_second": 12.222, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.1126133644911813, |
| "eval_physics_entropy": 0.6460600133538246, |
| "eval_physics_loss": 0.7363591194152832, |
| "eval_physics_mean_token_accuracy": 0.7971433384418487, |
| "eval_physics_num_tokens": 16625999.0, |
| "eval_physics_runtime": 45.3623, |
| "eval_physics_samples_per_second": 11.022, |
| "eval_physics_steps_per_second": 11.022, |
| "step": 2500 |
| }, |
| { |
| "entropy": 0.43424391131848095, |
| "epoch": 1.1170644856173149, |
| "grad_norm": 47.25, |
| "learning_rate": 1.6646666666666668e-05, |
| "loss": 7.1771, |
| "mean_token_accuracy": 0.8632295705378056, |
| "num_tokens": 16697896.0, |
| "step": 2510 |
| }, |
| { |
| "entropy": 0.5341594348661601, |
| "epoch": 1.1215156067434484, |
| "grad_norm": 37.75, |
| "learning_rate": 1.6624444444444445e-05, |
| "loss": 8.2842, |
| "mean_token_accuracy": 0.8503769244998693, |
| "num_tokens": 16763539.0, |
| "step": 2520 |
| }, |
| { |
| "entropy": 0.43298997059464456, |
| "epoch": 1.1259667278695822, |
| "grad_norm": 50.5, |
| "learning_rate": 1.6602222222222223e-05, |
| "loss": 7.088, |
| "mean_token_accuracy": 0.8653607998043299, |
| "num_tokens": 16829702.0, |
| "step": 2530 |
| }, |
| { |
| "entropy": 0.4383844044990838, |
| "epoch": 1.1304178489957157, |
| "grad_norm": 40.0, |
| "learning_rate": 1.658e-05, |
| "loss": 6.8564, |
| "mean_token_accuracy": 0.8711727976799011, |
| "num_tokens": 16899120.0, |
| "step": 2540 |
| }, |
| { |
| "entropy": 0.43383045233786105, |
| "epoch": 1.1348689701218495, |
| "grad_norm": 44.25, |
| "learning_rate": 1.6557777777777778e-05, |
| "loss": 6.9592, |
| "mean_token_accuracy": 0.8699989929795265, |
| "num_tokens": 16964702.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 0.44463928136974573, |
| "epoch": 1.139320091247983, |
| "grad_norm": 58.25, |
| "learning_rate": 1.6535555555555556e-05, |
| "loss": 7.1973, |
| "mean_token_accuracy": 0.8632942773401737, |
| "num_tokens": 17028582.0, |
| "step": 2560 |
| }, |
| { |
| "entropy": 0.4506220110692084, |
| "epoch": 1.1437712123741166, |
| "grad_norm": 45.25, |
| "learning_rate": 1.6513333333333333e-05, |
| "loss": 7.0271, |
| "mean_token_accuracy": 0.86661183424294, |
| "num_tokens": 17094349.0, |
| "step": 2570 |
| }, |
| { |
| "entropy": 0.4755444384180009, |
| "epoch": 1.1482223335002504, |
| "grad_norm": 57.75, |
| "learning_rate": 1.6491111111111114e-05, |
| "loss": 7.558, |
| "mean_token_accuracy": 0.8585624609142541, |
| "num_tokens": 17161099.0, |
| "step": 2580 |
| }, |
| { |
| "entropy": 0.45408363910391925, |
| "epoch": 1.152673454626384, |
| "grad_norm": 52.75, |
| "learning_rate": 1.646888888888889e-05, |
| "loss": 7.189, |
| "mean_token_accuracy": 0.8651944696903229, |
| "num_tokens": 17226592.0, |
| "step": 2590 |
| }, |
| { |
| "entropy": 0.4568724952172488, |
| "epoch": 1.1571245757525177, |
| "grad_norm": 47.75, |
| "learning_rate": 1.644666666666667e-05, |
| "loss": 7.341, |
| "mean_token_accuracy": 0.8606889557093382, |
| "num_tokens": 17293076.0, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.1571245757525177, |
| "eval_biology_entropy": 1.0697710152864457, |
| "eval_biology_loss": 1.365221381187439, |
| "eval_biology_mean_token_accuracy": 0.6732929725050926, |
| "eval_biology_num_tokens": 17293076.0, |
| "eval_biology_runtime": 36.3263, |
| "eval_biology_samples_per_second": 13.764, |
| "eval_biology_steps_per_second": 13.764, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.1571245757525177, |
| "eval_chemistry_entropy": 0.570949670881033, |
| "eval_chemistry_loss": 0.6830383539199829, |
| "eval_chemistry_mean_token_accuracy": 0.806793824672699, |
| "eval_chemistry_num_tokens": 17293076.0, |
| "eval_chemistry_runtime": 40.0485, |
| "eval_chemistry_samples_per_second": 12.485, |
| "eval_chemistry_steps_per_second": 12.485, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.1571245757525177, |
| "eval_math_entropy": 0.6329476754069329, |
| "eval_math_loss": 0.8906417489051819, |
| "eval_math_mean_token_accuracy": 0.7737527945041657, |
| "eval_math_num_tokens": 17293076.0, |
| "eval_math_runtime": 40.9341, |
| "eval_math_samples_per_second": 12.215, |
| "eval_math_steps_per_second": 12.215, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.1571245757525177, |
| "eval_physics_entropy": 0.6236911899447442, |
| "eval_physics_loss": 0.7392662763595581, |
| "eval_physics_mean_token_accuracy": 0.7970710125565529, |
| "eval_physics_num_tokens": 17293076.0, |
| "eval_physics_runtime": 45.3896, |
| "eval_physics_samples_per_second": 11.016, |
| "eval_physics_steps_per_second": 11.016, |
| "step": 2600 |
| }, |
| { |
| "entropy": 0.46716026999056337, |
| "epoch": 1.1615756968786513, |
| "grad_norm": 52.75, |
| "learning_rate": 1.6424444444444444e-05, |
| "loss": 7.5765, |
| "mean_token_accuracy": 0.8578994277864694, |
| "num_tokens": 17360241.0, |
| "step": 2610 |
| }, |
| { |
| "entropy": 0.5118057833053171, |
| "epoch": 1.166026818004785, |
| "grad_norm": 55.5, |
| "learning_rate": 1.6402222222222225e-05, |
| "loss": 8.0068, |
| "mean_token_accuracy": 0.850288962200284, |
| "num_tokens": 17424840.0, |
| "step": 2620 |
| }, |
| { |
| "entropy": 0.44888203619048, |
| "epoch": 1.1704779391309186, |
| "grad_norm": 48.25, |
| "learning_rate": 1.638e-05, |
| "loss": 7.1906, |
| "mean_token_accuracy": 0.8636637803167104, |
| "num_tokens": 17493054.0, |
| "step": 2630 |
| }, |
| { |
| "entropy": 0.4757227952126414, |
| "epoch": 1.1749290602570523, |
| "grad_norm": 56.75, |
| "learning_rate": 1.635777777777778e-05, |
| "loss": 7.4519, |
| "mean_token_accuracy": 0.8621215842664242, |
| "num_tokens": 17557844.0, |
| "step": 2640 |
| }, |
| { |
| "entropy": 0.46474175415933133, |
| "epoch": 1.179380181383186, |
| "grad_norm": 53.0, |
| "learning_rate": 1.6335555555555558e-05, |
| "loss": 7.4896, |
| "mean_token_accuracy": 0.8609307702630759, |
| "num_tokens": 17627019.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 0.4869027477223426, |
| "epoch": 1.1838313025093194, |
| "grad_norm": 41.5, |
| "learning_rate": 1.6313333333333335e-05, |
| "loss": 7.8311, |
| "mean_token_accuracy": 0.8541733529418707, |
| "num_tokens": 17692635.0, |
| "step": 2660 |
| }, |
| { |
| "entropy": 0.460888571664691, |
| "epoch": 1.1882824236354532, |
| "grad_norm": 36.75, |
| "learning_rate": 1.6291111111111113e-05, |
| "loss": 7.2302, |
| "mean_token_accuracy": 0.8630230847746134, |
| "num_tokens": 17760815.0, |
| "step": 2670 |
| }, |
| { |
| "entropy": 0.45354193188250064, |
| "epoch": 1.1927335447615868, |
| "grad_norm": 50.25, |
| "learning_rate": 1.626888888888889e-05, |
| "loss": 7.4467, |
| "mean_token_accuracy": 0.8609401177614927, |
| "num_tokens": 17826556.0, |
| "step": 2680 |
| }, |
| { |
| "entropy": 0.47404834572225807, |
| "epoch": 1.1971846658877205, |
| "grad_norm": 44.75, |
| "learning_rate": 1.6246666666666668e-05, |
| "loss": 7.5006, |
| "mean_token_accuracy": 0.859951825812459, |
| "num_tokens": 17890493.0, |
| "step": 2690 |
| }, |
| { |
| "entropy": 0.4380600852891803, |
| "epoch": 1.201635787013854, |
| "grad_norm": 51.25, |
| "learning_rate": 1.6224444444444446e-05, |
| "loss": 6.9107, |
| "mean_token_accuracy": 0.8684058170765638, |
| "num_tokens": 17955924.0, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.201635787013854, |
| "eval_biology_entropy": 1.1052746748328208, |
| "eval_biology_loss": 1.3584575653076172, |
| "eval_biology_mean_token_accuracy": 0.6726424011588097, |
| "eval_biology_num_tokens": 17955924.0, |
| "eval_biology_runtime": 34.6007, |
| "eval_biology_samples_per_second": 14.451, |
| "eval_biology_steps_per_second": 14.451, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.201635787013854, |
| "eval_chemistry_entropy": 0.5668688995242119, |
| "eval_chemistry_loss": 0.6775882840156555, |
| "eval_chemistry_mean_token_accuracy": 0.8082256765365601, |
| "eval_chemistry_num_tokens": 17955924.0, |
| "eval_chemistry_runtime": 39.1883, |
| "eval_chemistry_samples_per_second": 12.759, |
| "eval_chemistry_steps_per_second": 12.759, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.201635787013854, |
| "eval_math_entropy": 0.6524295365214348, |
| "eval_math_loss": 0.881108283996582, |
| "eval_math_mean_token_accuracy": 0.7738139452934265, |
| "eval_math_num_tokens": 17955924.0, |
| "eval_math_runtime": 40.0682, |
| "eval_math_samples_per_second": 12.479, |
| "eval_math_steps_per_second": 12.479, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.201635787013854, |
| "eval_physics_entropy": 0.6324486365318298, |
| "eval_physics_loss": 0.7365773916244507, |
| "eval_physics_mean_token_accuracy": 0.7977310811281204, |
| "eval_physics_num_tokens": 17955924.0, |
| "eval_physics_runtime": 44.7227, |
| "eval_physics_samples_per_second": 11.18, |
| "eval_physics_steps_per_second": 11.18, |
| "step": 2700 |
| }, |
| { |
| "entropy": 0.4297574946656823, |
| "epoch": 1.2060869081399876, |
| "grad_norm": 52.25, |
| "learning_rate": 1.6202222222222223e-05, |
| "loss": 6.8157, |
| "mean_token_accuracy": 0.8686471082270145, |
| "num_tokens": 18024547.0, |
| "step": 2710 |
| }, |
| { |
| "entropy": 0.44543066741898657, |
| "epoch": 1.2105380292661214, |
| "grad_norm": 55.5, |
| "learning_rate": 1.618e-05, |
| "loss": 7.2492, |
| "mean_token_accuracy": 0.8644745510071516, |
| "num_tokens": 18093886.0, |
| "step": 2720 |
| }, |
| { |
| "entropy": 0.4488057087175548, |
| "epoch": 1.214989150392255, |
| "grad_norm": 57.0, |
| "learning_rate": 1.615777777777778e-05, |
| "loss": 7.1238, |
| "mean_token_accuracy": 0.8651327833533287, |
| "num_tokens": 18166010.0, |
| "step": 2730 |
| }, |
| { |
| "entropy": 0.4604875521734357, |
| "epoch": 1.2194402715183887, |
| "grad_norm": 50.5, |
| "learning_rate": 1.6135555555555556e-05, |
| "loss": 7.2683, |
| "mean_token_accuracy": 0.8643526900559664, |
| "num_tokens": 18236214.0, |
| "step": 2740 |
| }, |
| { |
| "entropy": 0.4386564726941288, |
| "epoch": 1.2238913926445223, |
| "grad_norm": 42.25, |
| "learning_rate": 1.6113333333333334e-05, |
| "loss": 7.0528, |
| "mean_token_accuracy": 0.8680078580975532, |
| "num_tokens": 18300911.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 0.48869893290102484, |
| "epoch": 1.228342513770656, |
| "grad_norm": 57.75, |
| "learning_rate": 1.609111111111111e-05, |
| "loss": 7.8219, |
| "mean_token_accuracy": 0.8543589014559985, |
| "num_tokens": 18361378.0, |
| "step": 2760 |
| }, |
| { |
| "entropy": 0.4808385167270899, |
| "epoch": 1.2327936348967896, |
| "grad_norm": 50.75, |
| "learning_rate": 1.606888888888889e-05, |
| "loss": 7.688, |
| "mean_token_accuracy": 0.8553193368017673, |
| "num_tokens": 18426528.0, |
| "step": 2770 |
| }, |
| { |
| "entropy": 0.4169508836232126, |
| "epoch": 1.2372447560229234, |
| "grad_norm": 48.75, |
| "learning_rate": 1.6046666666666667e-05, |
| "loss": 6.5889, |
| "mean_token_accuracy": 0.871665557473898, |
| "num_tokens": 18495853.0, |
| "step": 2780 |
| }, |
| { |
| "entropy": 0.4467652436345816, |
| "epoch": 1.241695877149057, |
| "grad_norm": 51.0, |
| "learning_rate": 1.6024444444444444e-05, |
| "loss": 7.1433, |
| "mean_token_accuracy": 0.866059947758913, |
| "num_tokens": 18561871.0, |
| "step": 2790 |
| }, |
| { |
| "entropy": 0.4788202878087759, |
| "epoch": 1.2461469982751905, |
| "grad_norm": 53.0, |
| "learning_rate": 1.6002222222222222e-05, |
| "loss": 7.8087, |
| "mean_token_accuracy": 0.8565300915390253, |
| "num_tokens": 18632874.0, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.2461469982751905, |
| "eval_biology_entropy": 1.1672708329558372, |
| "eval_biology_loss": 1.3573185205459595, |
| "eval_biology_mean_token_accuracy": 0.6733051394224167, |
| "eval_biology_num_tokens": 18632874.0, |
| "eval_biology_runtime": 34.832, |
| "eval_biology_samples_per_second": 14.355, |
| "eval_biology_steps_per_second": 14.355, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.2461469982751905, |
| "eval_chemistry_entropy": 0.609499085098505, |
| "eval_chemistry_loss": 0.6756662726402283, |
| "eval_chemistry_mean_token_accuracy": 0.8074743691682815, |
| "eval_chemistry_num_tokens": 18632874.0, |
| "eval_chemistry_runtime": 39.2103, |
| "eval_chemistry_samples_per_second": 12.752, |
| "eval_chemistry_steps_per_second": 12.752, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.2461469982751905, |
| "eval_math_entropy": 0.670945393115282, |
| "eval_math_loss": 0.8828299045562744, |
| "eval_math_mean_token_accuracy": 0.7726577544212341, |
| "eval_math_num_tokens": 18632874.0, |
| "eval_math_runtime": 40.0603, |
| "eval_math_samples_per_second": 12.481, |
| "eval_math_steps_per_second": 12.481, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.2461469982751905, |
| "eval_physics_entropy": 0.6550075355470181, |
| "eval_physics_loss": 0.7325583100318909, |
| "eval_physics_mean_token_accuracy": 0.797877459526062, |
| "eval_physics_num_tokens": 18632874.0, |
| "eval_physics_runtime": 44.7113, |
| "eval_physics_samples_per_second": 11.183, |
| "eval_physics_steps_per_second": 11.183, |
| "step": 2800 |
| }, |
| { |
| "entropy": 0.45302023282274606, |
| "epoch": 1.2505981194013243, |
| "grad_norm": 50.25, |
| "learning_rate": 1.5980000000000003e-05, |
| "loss": 7.1865, |
| "mean_token_accuracy": 0.862761227041483, |
| "num_tokens": 18705033.0, |
| "step": 2810 |
| }, |
| { |
| "entropy": 0.48882503909990194, |
| "epoch": 1.2550492405274578, |
| "grad_norm": 43.0, |
| "learning_rate": 1.5957777777777777e-05, |
| "loss": 7.695, |
| "mean_token_accuracy": 0.8569835972040891, |
| "num_tokens": 18775027.0, |
| "step": 2820 |
| }, |
| { |
| "entropy": 0.4404743739403784, |
| "epoch": 1.2595003616535916, |
| "grad_norm": 56.75, |
| "learning_rate": 1.5935555555555558e-05, |
| "loss": 6.9805, |
| "mean_token_accuracy": 0.8669560357928277, |
| "num_tokens": 18840707.0, |
| "step": 2830 |
| }, |
| { |
| "entropy": 0.43263876661658285, |
| "epoch": 1.2639514827797251, |
| "grad_norm": 45.5, |
| "learning_rate": 1.5913333333333332e-05, |
| "loss": 6.9839, |
| "mean_token_accuracy": 0.8680296912789345, |
| "num_tokens": 18907324.0, |
| "step": 2840 |
| }, |
| { |
| "entropy": 0.44829661594703796, |
| "epoch": 1.2684026039058587, |
| "grad_norm": 43.0, |
| "learning_rate": 1.5891111111111113e-05, |
| "loss": 7.2426, |
| "mean_token_accuracy": 0.8637668710201979, |
| "num_tokens": 18980315.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 0.49221535651013254, |
| "epoch": 1.2728537250319925, |
| "grad_norm": 48.75, |
| "learning_rate": 1.5868888888888888e-05, |
| "loss": 7.8545, |
| "mean_token_accuracy": 0.8538596600294113, |
| "num_tokens": 19047920.0, |
| "step": 2860 |
| }, |
| { |
| "entropy": 0.46776230782270434, |
| "epoch": 1.277304846158126, |
| "grad_norm": 47.25, |
| "learning_rate": 1.584666666666667e-05, |
| "loss": 7.4137, |
| "mean_token_accuracy": 0.862864425778389, |
| "num_tokens": 19116973.0, |
| "step": 2870 |
| }, |
| { |
| "entropy": 0.44887350546196103, |
| "epoch": 1.2817559672842598, |
| "grad_norm": 45.25, |
| "learning_rate": 1.5824444444444446e-05, |
| "loss": 7.0052, |
| "mean_token_accuracy": 0.8685751393437385, |
| "num_tokens": 19180813.0, |
| "step": 2880 |
| }, |
| { |
| "entropy": 0.43839155780151484, |
| "epoch": 1.2862070884103933, |
| "grad_norm": 45.5, |
| "learning_rate": 1.5802222222222224e-05, |
| "loss": 7.2234, |
| "mean_token_accuracy": 0.8632114622741938, |
| "num_tokens": 19257345.0, |
| "step": 2890 |
| }, |
| { |
| "entropy": 0.47098802402615547, |
| "epoch": 1.2906582095365269, |
| "grad_norm": 53.5, |
| "learning_rate": 1.578e-05, |
| "loss": 7.4687, |
| "mean_token_accuracy": 0.8614061828702688, |
| "num_tokens": 19324641.0, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.2906582095365269, |
| "eval_biology_entropy": 1.0535325192213059, |
| "eval_biology_loss": 1.364938735961914, |
| "eval_biology_mean_token_accuracy": 0.6737875396609306, |
| "eval_biology_num_tokens": 19324641.0, |
| "eval_biology_runtime": 34.5991, |
| "eval_biology_samples_per_second": 14.451, |
| "eval_biology_steps_per_second": 14.451, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.2906582095365269, |
| "eval_chemistry_entropy": 0.5586568569540977, |
| "eval_chemistry_loss": 0.6768707036972046, |
| "eval_chemistry_mean_token_accuracy": 0.8086684308052063, |
| "eval_chemistry_num_tokens": 19324641.0, |
| "eval_chemistry_runtime": 39.2143, |
| "eval_chemistry_samples_per_second": 12.75, |
| "eval_chemistry_steps_per_second": 12.75, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.2906582095365269, |
| "eval_math_entropy": 0.6371020955145359, |
| "eval_math_loss": 0.8820441961288452, |
| "eval_math_mean_token_accuracy": 0.774823348402977, |
| "eval_math_num_tokens": 19324641.0, |
| "eval_math_runtime": 40.0431, |
| "eval_math_samples_per_second": 12.487, |
| "eval_math_steps_per_second": 12.487, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.2906582095365269, |
| "eval_physics_entropy": 0.6084816266894341, |
| "eval_physics_loss": 0.7365245819091797, |
| "eval_physics_mean_token_accuracy": 0.798389404296875, |
| "eval_physics_num_tokens": 19324641.0, |
| "eval_physics_runtime": 44.683, |
| "eval_physics_samples_per_second": 11.19, |
| "eval_physics_steps_per_second": 11.19, |
| "step": 2900 |
| }, |
| { |
| "entropy": 0.4464407380204648, |
| "epoch": 1.2951093306626607, |
| "grad_norm": 51.5, |
| "learning_rate": 1.575777777777778e-05, |
| "loss": 7.1403, |
| "mean_token_accuracy": 0.8659891322255134, |
| "num_tokens": 19391043.0, |
| "step": 2910 |
| }, |
| { |
| "entropy": 0.42263313177973033, |
| "epoch": 1.2995604517887944, |
| "grad_norm": 49.75, |
| "learning_rate": 1.5735555555555557e-05, |
| "loss": 6.6942, |
| "mean_token_accuracy": 0.8722406975924969, |
| "num_tokens": 19461093.0, |
| "step": 2920 |
| }, |
| { |
| "entropy": 0.42156479889526965, |
| "epoch": 1.304011572914928, |
| "grad_norm": 51.25, |
| "learning_rate": 1.5713333333333334e-05, |
| "loss": 6.8577, |
| "mean_token_accuracy": 0.8693336583673954, |
| "num_tokens": 19527736.0, |
| "step": 2930 |
| }, |
| { |
| "entropy": 0.45951347397640346, |
| "epoch": 1.3084626940410615, |
| "grad_norm": 45.0, |
| "learning_rate": 1.5691111111111112e-05, |
| "loss": 7.2401, |
| "mean_token_accuracy": 0.863092751801014, |
| "num_tokens": 19595645.0, |
| "step": 2940 |
| }, |
| { |
| "entropy": 0.45320088928565383, |
| "epoch": 1.3129138151671953, |
| "grad_norm": 39.75, |
| "learning_rate": 1.5668888888888893e-05, |
| "loss": 7.36, |
| "mean_token_accuracy": 0.859842124953866, |
| "num_tokens": 19660322.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 0.48471318408846853, |
| "epoch": 1.3173649362933288, |
| "grad_norm": 50.0, |
| "learning_rate": 1.5646666666666667e-05, |
| "loss": 7.591, |
| "mean_token_accuracy": 0.8583960466086864, |
| "num_tokens": 19725399.0, |
| "step": 2960 |
| }, |
| { |
| "entropy": 0.4510627003386617, |
| "epoch": 1.3218160574194626, |
| "grad_norm": 60.0, |
| "learning_rate": 1.5624444444444448e-05, |
| "loss": 7.3142, |
| "mean_token_accuracy": 0.8625423897057771, |
| "num_tokens": 19791328.0, |
| "step": 2970 |
| }, |
| { |
| "entropy": 0.4390063122846186, |
| "epoch": 1.3262671785455962, |
| "grad_norm": 48.25, |
| "learning_rate": 1.5602222222222222e-05, |
| "loss": 6.8952, |
| "mean_token_accuracy": 0.8692856475710868, |
| "num_tokens": 19857430.0, |
| "step": 2980 |
| }, |
| { |
| "entropy": 0.42201746730133893, |
| "epoch": 1.3307182996717297, |
| "grad_norm": 52.75, |
| "learning_rate": 1.5580000000000003e-05, |
| "loss": 6.7604, |
| "mean_token_accuracy": 0.8704383052885533, |
| "num_tokens": 19922864.0, |
| "step": 2990 |
| }, |
| { |
| "entropy": 0.46109400782734156, |
| "epoch": 1.3351694207978635, |
| "grad_norm": 50.25, |
| "learning_rate": 1.5557777777777778e-05, |
| "loss": 7.3923, |
| "mean_token_accuracy": 0.8613455057144165, |
| "num_tokens": 19988673.0, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.3351694207978635, |
| "eval_biology_entropy": 1.06728362596035, |
| "eval_biology_loss": 1.368791937828064, |
| "eval_biology_mean_token_accuracy": 0.6731789640784264, |
| "eval_biology_num_tokens": 19988673.0, |
| "eval_biology_runtime": 34.5521, |
| "eval_biology_samples_per_second": 14.471, |
| "eval_biology_steps_per_second": 14.471, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.3351694207978635, |
| "eval_chemistry_entropy": 0.5624488351643085, |
| "eval_chemistry_loss": 0.6767123937606812, |
| "eval_chemistry_mean_token_accuracy": 0.8085433168411255, |
| "eval_chemistry_num_tokens": 19988673.0, |
| "eval_chemistry_runtime": 39.0391, |
| "eval_chemistry_samples_per_second": 12.808, |
| "eval_chemistry_steps_per_second": 12.808, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.3351694207978635, |
| "eval_math_entropy": 0.6364709870517253, |
| "eval_math_loss": 0.8895117044448853, |
| "eval_math_mean_token_accuracy": 0.7743395804166794, |
| "eval_math_num_tokens": 19988673.0, |
| "eval_math_runtime": 39.9944, |
| "eval_math_samples_per_second": 12.502, |
| "eval_math_steps_per_second": 12.502, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.3351694207978635, |
| "eval_physics_entropy": 0.626722466468811, |
| "eval_physics_loss": 0.7327871322631836, |
| "eval_physics_mean_token_accuracy": 0.7997205726504326, |
| "eval_physics_num_tokens": 19988673.0, |
| "eval_physics_runtime": 44.6322, |
| "eval_physics_samples_per_second": 11.203, |
| "eval_physics_steps_per_second": 11.203, |
| "step": 3000 |
| }, |
| { |
| "entropy": 0.43926741583272816, |
| "epoch": 1.339620541923997, |
| "grad_norm": 49.75, |
| "learning_rate": 1.553555555555556e-05, |
| "loss": 7.246, |
| "mean_token_accuracy": 0.8642737410962582, |
| "num_tokens": 20054087.0, |
| "step": 3010 |
| }, |
| { |
| "entropy": 0.45354489935562015, |
| "epoch": 1.3440716630501308, |
| "grad_norm": 54.25, |
| "learning_rate": 1.5513333333333333e-05, |
| "loss": 6.9163, |
| "mean_token_accuracy": 0.8680711884051562, |
| "num_tokens": 20117738.0, |
| "step": 3020 |
| }, |
| { |
| "entropy": 0.44707584753632545, |
| "epoch": 1.3485227841762644, |
| "grad_norm": 38.75, |
| "learning_rate": 1.5491111111111114e-05, |
| "loss": 7.3788, |
| "mean_token_accuracy": 0.8618733812123537, |
| "num_tokens": 20180919.0, |
| "step": 3030 |
| }, |
| { |
| "entropy": 0.47324765836820004, |
| "epoch": 1.352973905302398, |
| "grad_norm": 56.0, |
| "learning_rate": 1.546888888888889e-05, |
| "loss": 7.3113, |
| "mean_token_accuracy": 0.8636962048709392, |
| "num_tokens": 20248890.0, |
| "step": 3040 |
| }, |
| { |
| "entropy": 0.4611404868774116, |
| "epoch": 1.3574250264285317, |
| "grad_norm": 64.5, |
| "learning_rate": 1.544666666666667e-05, |
| "loss": 7.6514, |
| "mean_token_accuracy": 0.8571126002818346, |
| "num_tokens": 20312039.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 0.43800184028223155, |
| "epoch": 1.3618761475546655, |
| "grad_norm": 46.5, |
| "learning_rate": 1.5424444444444447e-05, |
| "loss": 6.8249, |
| "mean_token_accuracy": 0.8698824197053909, |
| "num_tokens": 20379865.0, |
| "step": 3060 |
| }, |
| { |
| "entropy": 0.4432126395404339, |
| "epoch": 1.366327268680799, |
| "grad_norm": 47.5, |
| "learning_rate": 1.5402222222222224e-05, |
| "loss": 7.1948, |
| "mean_token_accuracy": 0.8645881909877062, |
| "num_tokens": 20450098.0, |
| "step": 3070 |
| }, |
| { |
| "entropy": 0.46012493832968177, |
| "epoch": 1.3707783898069326, |
| "grad_norm": 48.5, |
| "learning_rate": 1.5380000000000002e-05, |
| "loss": 7.3023, |
| "mean_token_accuracy": 0.8642731744796037, |
| "num_tokens": 20515713.0, |
| "step": 3080 |
| }, |
| { |
| "entropy": 0.5047637314535678, |
| "epoch": 1.3752295109330663, |
| "grad_norm": 49.75, |
| "learning_rate": 1.535777777777778e-05, |
| "loss": 8.2179, |
| "mean_token_accuracy": 0.849650651961565, |
| "num_tokens": 20577338.0, |
| "step": 3090 |
| }, |
| { |
| "entropy": 0.44162155147641896, |
| "epoch": 1.3796806320591999, |
| "grad_norm": 45.0, |
| "learning_rate": 1.5335555555555557e-05, |
| "loss": 6.9492, |
| "mean_token_accuracy": 0.8680732823908329, |
| "num_tokens": 20640374.0, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.3796806320591999, |
| "eval_biology_entropy": 1.1186871860027314, |
| "eval_biology_loss": 1.3491246700286865, |
| "eval_biology_mean_token_accuracy": 0.674078994512558, |
| "eval_biology_num_tokens": 20640374.0, |
| "eval_biology_runtime": 34.6826, |
| "eval_biology_samples_per_second": 14.416, |
| "eval_biology_steps_per_second": 14.416, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.3796806320591999, |
| "eval_chemistry_entropy": 0.5712928669154644, |
| "eval_chemistry_loss": 0.6696655750274658, |
| "eval_chemistry_mean_token_accuracy": 0.81008220744133, |
| "eval_chemistry_num_tokens": 20640374.0, |
| "eval_chemistry_runtime": 39.2229, |
| "eval_chemistry_samples_per_second": 12.748, |
| "eval_chemistry_steps_per_second": 12.748, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.3796806320591999, |
| "eval_math_entropy": 0.6394165593087673, |
| "eval_math_loss": 0.8825576305389404, |
| "eval_math_mean_token_accuracy": 0.7744283481836319, |
| "eval_math_num_tokens": 20640374.0, |
| "eval_math_runtime": 40.079, |
| "eval_math_samples_per_second": 12.475, |
| "eval_math_steps_per_second": 12.475, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.3796806320591999, |
| "eval_physics_entropy": 0.6231670607030392, |
| "eval_physics_loss": 0.7315182089805603, |
| "eval_physics_mean_token_accuracy": 0.7991429569721222, |
| "eval_physics_num_tokens": 20640374.0, |
| "eval_physics_runtime": 44.6444, |
| "eval_physics_samples_per_second": 11.2, |
| "eval_physics_steps_per_second": 11.2, |
| "step": 3100 |
| }, |
| { |
| "entropy": 0.46097635179758073, |
| "epoch": 1.3841317531853337, |
| "grad_norm": 48.0, |
| "learning_rate": 1.5313333333333335e-05, |
| "loss": 7.3505, |
| "mean_token_accuracy": 0.8647650934755802, |
| "num_tokens": 20701599.0, |
| "step": 3110 |
| }, |
| { |
| "entropy": 0.4649339490570128, |
| "epoch": 1.3885828743114672, |
| "grad_norm": 49.25, |
| "learning_rate": 1.5291111111111112e-05, |
| "loss": 7.4677, |
| "mean_token_accuracy": 0.8611573718488217, |
| "num_tokens": 20769790.0, |
| "step": 3120 |
| }, |
| { |
| "entropy": 0.460366331692785, |
| "epoch": 1.3930339954376008, |
| "grad_norm": 37.0, |
| "learning_rate": 1.526888888888889e-05, |
| "loss": 7.3205, |
| "mean_token_accuracy": 0.8623717144131661, |
| "num_tokens": 20837901.0, |
| "step": 3130 |
| }, |
| { |
| "entropy": 0.4693802764639258, |
| "epoch": 1.3974851165637345, |
| "grad_norm": 49.0, |
| "learning_rate": 1.5246666666666668e-05, |
| "loss": 7.5547, |
| "mean_token_accuracy": 0.8608989223837853, |
| "num_tokens": 20900772.0, |
| "step": 3140 |
| }, |
| { |
| "entropy": 0.4827373533509672, |
| "epoch": 1.401936237689868, |
| "grad_norm": 48.75, |
| "learning_rate": 1.5224444444444447e-05, |
| "loss": 7.72, |
| "mean_token_accuracy": 0.8545261926949024, |
| "num_tokens": 20964368.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 0.4671311844140291, |
| "epoch": 1.4063873588160019, |
| "grad_norm": 43.75, |
| "learning_rate": 1.5202222222222223e-05, |
| "loss": 7.4467, |
| "mean_token_accuracy": 0.8617992985993623, |
| "num_tokens": 21032357.0, |
| "step": 3160 |
| }, |
| { |
| "entropy": 0.47543164398521187, |
| "epoch": 1.4108384799421354, |
| "grad_norm": 47.75, |
| "learning_rate": 1.5180000000000002e-05, |
| "loss": 7.7554, |
| "mean_token_accuracy": 0.8542252779006958, |
| "num_tokens": 21097884.0, |
| "step": 3170 |
| }, |
| { |
| "entropy": 0.4615335600916296, |
| "epoch": 1.415289601068269, |
| "grad_norm": 54.75, |
| "learning_rate": 1.5157777777777778e-05, |
| "loss": 7.3541, |
| "mean_token_accuracy": 0.8640846721827984, |
| "num_tokens": 21162515.0, |
| "step": 3180 |
| }, |
| { |
| "entropy": 0.4311759488657117, |
| "epoch": 1.4197407221944027, |
| "grad_norm": 58.75, |
| "learning_rate": 1.5135555555555557e-05, |
| "loss": 6.9569, |
| "mean_token_accuracy": 0.865353650227189, |
| "num_tokens": 21230408.0, |
| "step": 3190 |
| }, |
| { |
| "entropy": 0.48539937380701303, |
| "epoch": 1.4241918433205363, |
| "grad_norm": 43.75, |
| "learning_rate": 1.5113333333333335e-05, |
| "loss": 7.6302, |
| "mean_token_accuracy": 0.855873254314065, |
| "num_tokens": 21299050.0, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.4241918433205363, |
| "eval_biology_entropy": 1.1577025835514068, |
| "eval_biology_loss": 1.3504490852355957, |
| "eval_biology_mean_token_accuracy": 0.6741515842676162, |
| "eval_biology_num_tokens": 21299050.0, |
| "eval_biology_runtime": 34.6063, |
| "eval_biology_samples_per_second": 14.448, |
| "eval_biology_steps_per_second": 14.448, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.4241918433205363, |
| "eval_chemistry_entropy": 0.5812296238243579, |
| "eval_chemistry_loss": 0.6663944125175476, |
| "eval_chemistry_mean_token_accuracy": 0.8100144367218017, |
| "eval_chemistry_num_tokens": 21299050.0, |
| "eval_chemistry_runtime": 39.1379, |
| "eval_chemistry_samples_per_second": 12.775, |
| "eval_chemistry_steps_per_second": 12.775, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.4241918433205363, |
| "eval_math_entropy": 0.6552925122976303, |
| "eval_math_loss": 0.889281153678894, |
| "eval_math_mean_token_accuracy": 0.7729093509912491, |
| "eval_math_num_tokens": 21299050.0, |
| "eval_math_runtime": 40.036, |
| "eval_math_samples_per_second": 12.489, |
| "eval_math_steps_per_second": 12.489, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.4241918433205363, |
| "eval_physics_entropy": 0.6362262586951256, |
| "eval_physics_loss": 0.7275048494338989, |
| "eval_physics_mean_token_accuracy": 0.7997702179551125, |
| "eval_physics_num_tokens": 21299050.0, |
| "eval_physics_runtime": 44.6315, |
| "eval_physics_samples_per_second": 11.203, |
| "eval_physics_steps_per_second": 11.203, |
| "step": 3200 |
| }, |
| { |
| "entropy": 0.4445551418699324, |
| "epoch": 1.42864296444667, |
| "grad_norm": 61.0, |
| "learning_rate": 1.5091111111111113e-05, |
| "loss": 7.0941, |
| "mean_token_accuracy": 0.8637882396578789, |
| "num_tokens": 21366237.0, |
| "step": 3210 |
| }, |
| { |
| "entropy": 0.47023085290566086, |
| "epoch": 1.4330940855728036, |
| "grad_norm": 42.25, |
| "learning_rate": 1.506888888888889e-05, |
| "loss": 7.5448, |
| "mean_token_accuracy": 0.8603004097938538, |
| "num_tokens": 21436423.0, |
| "step": 3220 |
| }, |
| { |
| "entropy": 0.4534061783924699, |
| "epoch": 1.4375452066989374, |
| "grad_norm": 59.25, |
| "learning_rate": 1.5046666666666668e-05, |
| "loss": 7.2007, |
| "mean_token_accuracy": 0.8642718207091094, |
| "num_tokens": 21504658.0, |
| "step": 3230 |
| }, |
| { |
| "entropy": 0.4432052950374782, |
| "epoch": 1.441996327825071, |
| "grad_norm": 54.0, |
| "learning_rate": 1.5024444444444445e-05, |
| "loss": 7.2676, |
| "mean_token_accuracy": 0.8634330548346043, |
| "num_tokens": 21569748.0, |
| "step": 3240 |
| }, |
| { |
| "entropy": 0.4982606652658433, |
| "epoch": 1.4464474489512047, |
| "grad_norm": 47.5, |
| "learning_rate": 1.5002222222222223e-05, |
| "loss": 7.6666, |
| "mean_token_accuracy": 0.8573396757245064, |
| "num_tokens": 21630649.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 0.4611293891444802, |
| "epoch": 1.4508985700773382, |
| "grad_norm": 57.5, |
| "learning_rate": 1.498e-05, |
| "loss": 7.5086, |
| "mean_token_accuracy": 0.8603343788534403, |
| "num_tokens": 21694065.0, |
| "step": 3260 |
| }, |
| { |
| "entropy": 0.43817890184000136, |
| "epoch": 1.4553496912034718, |
| "grad_norm": 48.75, |
| "learning_rate": 1.495777777777778e-05, |
| "loss": 7.1006, |
| "mean_token_accuracy": 0.8694320507347584, |
| "num_tokens": 21758494.0, |
| "step": 3270 |
| }, |
| { |
| "entropy": 0.46289148470386865, |
| "epoch": 1.4598008123296056, |
| "grad_norm": 61.25, |
| "learning_rate": 1.4935555555555556e-05, |
| "loss": 7.1929, |
| "mean_token_accuracy": 0.8642273522913456, |
| "num_tokens": 21822217.0, |
| "step": 3280 |
| }, |
| { |
| "entropy": 0.4299561256542802, |
| "epoch": 1.4642519334557391, |
| "grad_norm": 59.25, |
| "learning_rate": 1.4913333333333335e-05, |
| "loss": 7.0739, |
| "mean_token_accuracy": 0.8657123785465956, |
| "num_tokens": 21887417.0, |
| "step": 3290 |
| }, |
| { |
| "entropy": 0.44486900251358746, |
| "epoch": 1.468703054581873, |
| "grad_norm": 43.0, |
| "learning_rate": 1.4891111111111111e-05, |
| "loss": 7.0361, |
| "mean_token_accuracy": 0.8671017855405807, |
| "num_tokens": 21954784.0, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.468703054581873, |
| "eval_biology_entropy": 1.11163039290905, |
| "eval_biology_loss": 1.3528118133544922, |
| "eval_biology_mean_token_accuracy": 0.6748502798080445, |
| "eval_biology_num_tokens": 21954784.0, |
| "eval_biology_runtime": 34.4615, |
| "eval_biology_samples_per_second": 14.509, |
| "eval_biology_steps_per_second": 14.509, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.468703054581873, |
| "eval_chemistry_entropy": 0.5637654248774052, |
| "eval_chemistry_loss": 0.6681108474731445, |
| "eval_chemistry_mean_token_accuracy": 0.8105579479932785, |
| "eval_chemistry_num_tokens": 21954784.0, |
| "eval_chemistry_runtime": 39.111, |
| "eval_chemistry_samples_per_second": 12.784, |
| "eval_chemistry_steps_per_second": 12.784, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.468703054581873, |
| "eval_math_entropy": 0.6439891613125801, |
| "eval_math_loss": 0.8829548358917236, |
| "eval_math_mean_token_accuracy": 0.7747701604366303, |
| "eval_math_num_tokens": 21954784.0, |
| "eval_math_runtime": 40.0349, |
| "eval_math_samples_per_second": 12.489, |
| "eval_math_steps_per_second": 12.489, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.468703054581873, |
| "eval_physics_entropy": 0.6284398764371872, |
| "eval_physics_loss": 0.7272571921348572, |
| "eval_physics_mean_token_accuracy": 0.8000440203547478, |
| "eval_physics_num_tokens": 21954784.0, |
| "eval_physics_runtime": 44.6221, |
| "eval_physics_samples_per_second": 11.205, |
| "eval_physics_steps_per_second": 11.205, |
| "step": 3300 |
| }, |
| { |
| "entropy": 0.46610420299693944, |
| "epoch": 1.4731541757080064, |
| "grad_norm": 48.75, |
| "learning_rate": 1.486888888888889e-05, |
| "loss": 7.5979, |
| "mean_token_accuracy": 0.857284490019083, |
| "num_tokens": 22022454.0, |
| "step": 3310 |
| }, |
| { |
| "entropy": 0.46699747079983356, |
| "epoch": 1.47760529683414, |
| "grad_norm": 42.0, |
| "learning_rate": 1.4846666666666666e-05, |
| "loss": 7.2711, |
| "mean_token_accuracy": 0.8635724060237407, |
| "num_tokens": 22090334.0, |
| "step": 3320 |
| }, |
| { |
| "entropy": 0.472093007247895, |
| "epoch": 1.4820564179602738, |
| "grad_norm": 52.5, |
| "learning_rate": 1.4824444444444446e-05, |
| "loss": 7.7223, |
| "mean_token_accuracy": 0.8550102084875106, |
| "num_tokens": 22157686.0, |
| "step": 3330 |
| }, |
| { |
| "entropy": 0.4755250898189843, |
| "epoch": 1.4865075390864073, |
| "grad_norm": 48.75, |
| "learning_rate": 1.4802222222222225e-05, |
| "loss": 7.4331, |
| "mean_token_accuracy": 0.8597620997577906, |
| "num_tokens": 22223473.0, |
| "step": 3340 |
| }, |
| { |
| "entropy": 0.4333983602002263, |
| "epoch": 1.490958660212541, |
| "grad_norm": 45.75, |
| "learning_rate": 1.478e-05, |
| "loss": 7.0257, |
| "mean_token_accuracy": 0.8673679675906897, |
| "num_tokens": 22289965.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 0.48727822387591, |
| "epoch": 1.4954097813386746, |
| "grad_norm": 52.75, |
| "learning_rate": 1.475777777777778e-05, |
| "loss": 7.6776, |
| "mean_token_accuracy": 0.8565780740231276, |
| "num_tokens": 22357538.0, |
| "step": 3360 |
| }, |
| { |
| "entropy": 0.4657940316013992, |
| "epoch": 1.4998609024648082, |
| "grad_norm": 50.25, |
| "learning_rate": 1.4735555555555556e-05, |
| "loss": 7.5463, |
| "mean_token_accuracy": 0.8585332401096821, |
| "num_tokens": 22425667.0, |
| "step": 3370 |
| }, |
| { |
| "entropy": 0.4623819244094193, |
| "epoch": 1.504312023590942, |
| "grad_norm": 40.25, |
| "learning_rate": 1.4713333333333335e-05, |
| "loss": 7.3553, |
| "mean_token_accuracy": 0.8621751669794321, |
| "num_tokens": 22493127.0, |
| "step": 3380 |
| }, |
| { |
| "entropy": 0.4559232075698674, |
| "epoch": 1.5087631447170757, |
| "grad_norm": 57.5, |
| "learning_rate": 1.4691111111111111e-05, |
| "loss": 7.3937, |
| "mean_token_accuracy": 0.8613190371543169, |
| "num_tokens": 22556146.0, |
| "step": 3390 |
| }, |
| { |
| "entropy": 0.44279447542503475, |
| "epoch": 1.5132142658432093, |
| "grad_norm": 65.5, |
| "learning_rate": 1.466888888888889e-05, |
| "loss": 7.0113, |
| "mean_token_accuracy": 0.867198595777154, |
| "num_tokens": 22620726.0, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.5132142658432093, |
| "eval_biology_entropy": 1.1123783532381057, |
| "eval_biology_loss": 1.3514546155929565, |
| "eval_biology_mean_token_accuracy": 0.6745553755164146, |
| "eval_biology_num_tokens": 22620726.0, |
| "eval_biology_runtime": 34.6165, |
| "eval_biology_samples_per_second": 14.444, |
| "eval_biology_steps_per_second": 14.444, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.5132142658432093, |
| "eval_chemistry_entropy": 0.5597048043310642, |
| "eval_chemistry_loss": 0.6646822690963745, |
| "eval_chemistry_mean_token_accuracy": 0.810983188033104, |
| "eval_chemistry_num_tokens": 22620726.0, |
| "eval_chemistry_runtime": 39.4242, |
| "eval_chemistry_samples_per_second": 12.683, |
| "eval_chemistry_steps_per_second": 12.683, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.5132142658432093, |
| "eval_math_entropy": 0.6601651799380779, |
| "eval_math_loss": 0.8772966265678406, |
| "eval_math_mean_token_accuracy": 0.7746776162385941, |
| "eval_math_num_tokens": 22620726.0, |
| "eval_math_runtime": 40.0695, |
| "eval_math_samples_per_second": 12.478, |
| "eval_math_steps_per_second": 12.478, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.5132142658432093, |
| "eval_physics_entropy": 0.6273573201596737, |
| "eval_physics_loss": 0.7271793484687805, |
| "eval_physics_mean_token_accuracy": 0.8000048289895058, |
| "eval_physics_num_tokens": 22620726.0, |
| "eval_physics_runtime": 44.6453, |
| "eval_physics_samples_per_second": 11.199, |
| "eval_physics_steps_per_second": 11.199, |
| "step": 3400 |
| }, |
| { |
| "entropy": 0.4566797907464206, |
| "epoch": 1.5176653869693428, |
| "grad_norm": 40.0, |
| "learning_rate": 1.4646666666666666e-05, |
| "loss": 7.4454, |
| "mean_token_accuracy": 0.8616115640848875, |
| "num_tokens": 22692897.0, |
| "step": 3410 |
| }, |
| { |
| "entropy": 0.4497338145039976, |
| "epoch": 1.5221165080954764, |
| "grad_norm": 51.25, |
| "learning_rate": 1.4624444444444446e-05, |
| "loss": 7.0273, |
| "mean_token_accuracy": 0.8670224133878947, |
| "num_tokens": 22757148.0, |
| "step": 3420 |
| }, |
| { |
| "entropy": 0.4624111349694431, |
| "epoch": 1.5265676292216102, |
| "grad_norm": 49.5, |
| "learning_rate": 1.4602222222222225e-05, |
| "loss": 7.5322, |
| "mean_token_accuracy": 0.8592155817896128, |
| "num_tokens": 22821150.0, |
| "step": 3430 |
| }, |
| { |
| "entropy": 0.43611071100458504, |
| "epoch": 1.531018750347744, |
| "grad_norm": 45.25, |
| "learning_rate": 1.4580000000000001e-05, |
| "loss": 6.8629, |
| "mean_token_accuracy": 0.8688468389213085, |
| "num_tokens": 22895186.0, |
| "step": 3440 |
| }, |
| { |
| "entropy": 0.4139011885970831, |
| "epoch": 1.5354698714738775, |
| "grad_norm": 56.0, |
| "learning_rate": 1.455777777777778e-05, |
| "loss": 6.5914, |
| "mean_token_accuracy": 0.8730472829192877, |
| "num_tokens": 22963108.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 0.43545150980353353, |
| "epoch": 1.539920992600011, |
| "grad_norm": 43.0, |
| "learning_rate": 1.4535555555555556e-05, |
| "loss": 6.9535, |
| "mean_token_accuracy": 0.8692302446812391, |
| "num_tokens": 23020006.0, |
| "step": 3460 |
| }, |
| { |
| "entropy": 0.44004984106868505, |
| "epoch": 1.5443721137261448, |
| "grad_norm": 48.5, |
| "learning_rate": 1.4513333333333336e-05, |
| "loss": 7.058, |
| "mean_token_accuracy": 0.8658375445753336, |
| "num_tokens": 23084950.0, |
| "step": 3470 |
| }, |
| { |
| "entropy": 0.45269664339721205, |
| "epoch": 1.5488232348522786, |
| "grad_norm": 47.75, |
| "learning_rate": 1.4491111111111111e-05, |
| "loss": 7.1621, |
| "mean_token_accuracy": 0.8656145602464675, |
| "num_tokens": 23145883.0, |
| "step": 3480 |
| }, |
| { |
| "entropy": 0.4229992181994021, |
| "epoch": 1.5532743559784121, |
| "grad_norm": 44.75, |
| "learning_rate": 1.446888888888889e-05, |
| "loss": 6.9238, |
| "mean_token_accuracy": 0.8702617697417736, |
| "num_tokens": 23208622.0, |
| "step": 3490 |
| }, |
| { |
| "entropy": 0.44544641869142654, |
| "epoch": 1.5577254771045457, |
| "grad_norm": 63.25, |
| "learning_rate": 1.4446666666666668e-05, |
| "loss": 7.0211, |
| "mean_token_accuracy": 0.8676475413143635, |
| "num_tokens": 23274053.0, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.5577254771045457, |
| "eval_biology_entropy": 1.0966479950547219, |
| "eval_biology_loss": 1.3587557077407837, |
| "eval_biology_mean_token_accuracy": 0.6734435469508171, |
| "eval_biology_num_tokens": 23274053.0, |
| "eval_biology_runtime": 34.6526, |
| "eval_biology_samples_per_second": 14.429, |
| "eval_biology_steps_per_second": 14.429, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.5577254771045457, |
| "eval_chemistry_entropy": 0.5619084319472313, |
| "eval_chemistry_loss": 0.665738582611084, |
| "eval_chemistry_mean_token_accuracy": 0.8110532833337784, |
| "eval_chemistry_num_tokens": 23274053.0, |
| "eval_chemistry_runtime": 38.9715, |
| "eval_chemistry_samples_per_second": 12.83, |
| "eval_chemistry_steps_per_second": 12.83, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.5577254771045457, |
| "eval_math_entropy": 0.6567717355191708, |
| "eval_math_loss": 0.8799146413803101, |
| "eval_math_mean_token_accuracy": 0.7743340896368027, |
| "eval_math_num_tokens": 23274053.0, |
| "eval_math_runtime": 39.9007, |
| "eval_math_samples_per_second": 12.531, |
| "eval_math_steps_per_second": 12.531, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.5577254771045457, |
| "eval_physics_entropy": 0.62735349214077, |
| "eval_physics_loss": 0.7280191779136658, |
| "eval_physics_mean_token_accuracy": 0.7997954402565957, |
| "eval_physics_num_tokens": 23274053.0, |
| "eval_physics_runtime": 44.5826, |
| "eval_physics_samples_per_second": 11.215, |
| "eval_physics_steps_per_second": 11.215, |
| "step": 3500 |
| }, |
| { |
| "entropy": 0.458773175207898, |
| "epoch": 1.5621765982306792, |
| "grad_norm": 53.75, |
| "learning_rate": 1.4424444444444446e-05, |
| "loss": 7.5433, |
| "mean_token_accuracy": 0.8593448866158724, |
| "num_tokens": 23341632.0, |
| "step": 3510 |
| }, |
| { |
| "entropy": 0.43992816051468253, |
| "epoch": 1.566627719356813, |
| "grad_norm": 46.25, |
| "learning_rate": 1.4402222222222224e-05, |
| "loss": 6.7706, |
| "mean_token_accuracy": 0.871754739433527, |
| "num_tokens": 23410761.0, |
| "step": 3520 |
| }, |
| { |
| "entropy": 0.44051281539723275, |
| "epoch": 1.5710788404829468, |
| "grad_norm": 65.5, |
| "learning_rate": 1.4380000000000001e-05, |
| "loss": 7.1011, |
| "mean_token_accuracy": 0.8648776780813933, |
| "num_tokens": 23474045.0, |
| "step": 3530 |
| }, |
| { |
| "entropy": 0.45597848305478694, |
| "epoch": 1.5755299616090803, |
| "grad_norm": 47.0, |
| "learning_rate": 1.4357777777777779e-05, |
| "loss": 7.3695, |
| "mean_token_accuracy": 0.8619882300496101, |
| "num_tokens": 23541078.0, |
| "step": 3540 |
| }, |
| { |
| "entropy": 0.4527738081756979, |
| "epoch": 1.5799810827352139, |
| "grad_norm": 57.5, |
| "learning_rate": 1.4335555555555556e-05, |
| "loss": 7.249, |
| "mean_token_accuracy": 0.8615109730511904, |
| "num_tokens": 23609956.0, |
| "step": 3550 |
| }, |
| { |
| "entropy": 0.4503319292329252, |
| "epoch": 1.5844322038613474, |
| "grad_norm": 41.5, |
| "learning_rate": 1.4313333333333334e-05, |
| "loss": 7.2859, |
| "mean_token_accuracy": 0.8638025216758252, |
| "num_tokens": 23679603.0, |
| "step": 3560 |
| }, |
| { |
| "entropy": 0.4868523414246738, |
| "epoch": 1.5888833249874812, |
| "grad_norm": 44.0, |
| "learning_rate": 1.4291111111111113e-05, |
| "loss": 7.6927, |
| "mean_token_accuracy": 0.8583999592810869, |
| "num_tokens": 23744554.0, |
| "step": 3570 |
| }, |
| { |
| "entropy": 0.41968008074909446, |
| "epoch": 1.593334446113615, |
| "grad_norm": 45.25, |
| "learning_rate": 1.426888888888889e-05, |
| "loss": 6.7521, |
| "mean_token_accuracy": 0.8683962229639292, |
| "num_tokens": 23813464.0, |
| "step": 3580 |
| }, |
| { |
| "entropy": 0.4784168460406363, |
| "epoch": 1.5977855672397485, |
| "grad_norm": 53.75, |
| "learning_rate": 1.4246666666666669e-05, |
| "loss": 7.682, |
| "mean_token_accuracy": 0.8594525013118982, |
| "num_tokens": 23875868.0, |
| "step": 3590 |
| }, |
| { |
| "entropy": 0.475644052028656, |
| "epoch": 1.602236688365882, |
| "grad_norm": 50.75, |
| "learning_rate": 1.4224444444444445e-05, |
| "loss": 7.4061, |
| "mean_token_accuracy": 0.8622573211789131, |
| "num_tokens": 23940396.0, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.602236688365882, |
| "eval_biology_entropy": 1.1075647550821304, |
| "eval_biology_loss": 1.3473989963531494, |
| "eval_biology_mean_token_accuracy": 0.6743575021624565, |
| "eval_biology_num_tokens": 23940396.0, |
| "eval_biology_runtime": 34.5191, |
| "eval_biology_samples_per_second": 14.485, |
| "eval_biology_steps_per_second": 14.485, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.602236688365882, |
| "eval_chemistry_entropy": 0.5602062820792199, |
| "eval_chemistry_loss": 0.6587600111961365, |
| "eval_chemistry_mean_token_accuracy": 0.8124842391014099, |
| "eval_chemistry_num_tokens": 23940396.0, |
| "eval_chemistry_runtime": 39.1498, |
| "eval_chemistry_samples_per_second": 12.771, |
| "eval_chemistry_steps_per_second": 12.771, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.602236688365882, |
| "eval_math_entropy": 0.6360780152976513, |
| "eval_math_loss": 0.8845098614692688, |
| "eval_math_mean_token_accuracy": 0.7751622016429901, |
| "eval_math_num_tokens": 23940396.0, |
| "eval_math_runtime": 40.0408, |
| "eval_math_samples_per_second": 12.487, |
| "eval_math_steps_per_second": 12.487, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.602236688365882, |
| "eval_physics_entropy": 0.6137304565608501, |
| "eval_physics_loss": 0.7243133783340454, |
| "eval_physics_mean_token_accuracy": 0.8015137906670571, |
| "eval_physics_num_tokens": 23940396.0, |
| "eval_physics_runtime": 44.6545, |
| "eval_physics_samples_per_second": 11.197, |
| "eval_physics_steps_per_second": 11.197, |
| "step": 3600 |
| }, |
| { |
| "entropy": 0.4340103717520833, |
| "epoch": 1.6066878094920158, |
| "grad_norm": 45.5, |
| "learning_rate": 1.4202222222222224e-05, |
| "loss": 7.132, |
| "mean_token_accuracy": 0.8654290784150362, |
| "num_tokens": 24005993.0, |
| "step": 3610 |
| }, |
| { |
| "entropy": 0.4127938458696008, |
| "epoch": 1.6111389306181496, |
| "grad_norm": 44.5, |
| "learning_rate": 1.418e-05, |
| "loss": 6.5634, |
| "mean_token_accuracy": 0.8747978035360575, |
| "num_tokens": 24076192.0, |
| "step": 3620 |
| }, |
| { |
| "entropy": 0.446969473361969, |
| "epoch": 1.6155900517442832, |
| "grad_norm": 47.5, |
| "learning_rate": 1.4157777777777779e-05, |
| "loss": 7.0782, |
| "mean_token_accuracy": 0.8648997772485018, |
| "num_tokens": 24147204.0, |
| "step": 3630 |
| }, |
| { |
| "entropy": 0.4407890189439058, |
| "epoch": 1.6200411728704167, |
| "grad_norm": 55.5, |
| "learning_rate": 1.4135555555555555e-05, |
| "loss": 7.1071, |
| "mean_token_accuracy": 0.865436827018857, |
| "num_tokens": 24215449.0, |
| "step": 3640 |
| }, |
| { |
| "entropy": 0.4491986585780978, |
| "epoch": 1.6244922939965503, |
| "grad_norm": 64.5, |
| "learning_rate": 1.4113333333333334e-05, |
| "loss": 7.1178, |
| "mean_token_accuracy": 0.8655546098947525, |
| "num_tokens": 24278738.0, |
| "step": 3650 |
| }, |
| { |
| "entropy": 0.4485160048119724, |
| "epoch": 1.628943415122684, |
| "grad_norm": 46.0, |
| "learning_rate": 1.4091111111111114e-05, |
| "loss": 7.3503, |
| "mean_token_accuracy": 0.8617370069026947, |
| "num_tokens": 24343555.0, |
| "step": 3660 |
| }, |
| { |
| "entropy": 0.45399625692516565, |
| "epoch": 1.6333945362488178, |
| "grad_norm": 52.75, |
| "learning_rate": 1.406888888888889e-05, |
| "loss": 7.0741, |
| "mean_token_accuracy": 0.8646973222494125, |
| "num_tokens": 24407294.0, |
| "step": 3670 |
| }, |
| { |
| "entropy": 0.4452649365179241, |
| "epoch": 1.6378456573749514, |
| "grad_norm": 45.75, |
| "learning_rate": 1.4046666666666669e-05, |
| "loss": 7.1128, |
| "mean_token_accuracy": 0.8665703751146794, |
| "num_tokens": 24468795.0, |
| "step": 3680 |
| }, |
| { |
| "entropy": 0.41706427866593004, |
| "epoch": 1.642296778501085, |
| "grad_norm": 51.75, |
| "learning_rate": 1.4024444444444445e-05, |
| "loss": 6.7922, |
| "mean_token_accuracy": 0.8704725258052349, |
| "num_tokens": 24537515.0, |
| "step": 3690 |
| }, |
| { |
| "entropy": 0.455549178365618, |
| "epoch": 1.6467478996272185, |
| "grad_norm": 46.25, |
| "learning_rate": 1.4002222222222224e-05, |
| "loss": 7.1394, |
| "mean_token_accuracy": 0.8660995673388243, |
| "num_tokens": 24604118.0, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.6467478996272185, |
| "eval_biology_entropy": 1.13196478754282, |
| "eval_biology_loss": 1.3496977090835571, |
| "eval_biology_mean_token_accuracy": 0.6747560929656029, |
| "eval_biology_num_tokens": 24604118.0, |
| "eval_biology_runtime": 34.4565, |
| "eval_biology_samples_per_second": 14.511, |
| "eval_biology_steps_per_second": 14.511, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.6467478996272185, |
| "eval_chemistry_entropy": 0.574998948186636, |
| "eval_chemistry_loss": 0.6572164297103882, |
| "eval_chemistry_mean_token_accuracy": 0.8128995629549026, |
| "eval_chemistry_num_tokens": 24604118.0, |
| "eval_chemistry_runtime": 39.102, |
| "eval_chemistry_samples_per_second": 12.787, |
| "eval_chemistry_steps_per_second": 12.787, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.6467478996272185, |
| "eval_math_entropy": 0.672197436183691, |
| "eval_math_loss": 0.8755368590354919, |
| "eval_math_mean_token_accuracy": 0.7757299134731293, |
| "eval_math_num_tokens": 24604118.0, |
| "eval_math_runtime": 40.0589, |
| "eval_math_samples_per_second": 12.482, |
| "eval_math_steps_per_second": 12.482, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.6467478996272185, |
| "eval_physics_entropy": 0.638806305885315, |
| "eval_physics_loss": 0.7225396633148193, |
| "eval_physics_mean_token_accuracy": 0.8007936144471168, |
| "eval_physics_num_tokens": 24604118.0, |
| "eval_physics_runtime": 44.7032, |
| "eval_physics_samples_per_second": 11.185, |
| "eval_physics_steps_per_second": 11.185, |
| "step": 3700 |
| }, |
| { |
| "entropy": 0.40778020760044453, |
| "epoch": 1.6511990207533522, |
| "grad_norm": 52.25, |
| "learning_rate": 1.398e-05, |
| "loss": 6.5648, |
| "mean_token_accuracy": 0.8739966981112957, |
| "num_tokens": 24672806.0, |
| "step": 3710 |
| }, |
| { |
| "entropy": 0.41995010059326887, |
| "epoch": 1.655650141879486, |
| "grad_norm": 41.0, |
| "learning_rate": 1.395777777777778e-05, |
| "loss": 6.7922, |
| "mean_token_accuracy": 0.8724275059998036, |
| "num_tokens": 24741914.0, |
| "step": 3720 |
| }, |
| { |
| "entropy": 0.4350844810716808, |
| "epoch": 1.6601012630056196, |
| "grad_norm": 45.5, |
| "learning_rate": 1.3935555555555557e-05, |
| "loss": 6.8855, |
| "mean_token_accuracy": 0.8713530752807855, |
| "num_tokens": 24809566.0, |
| "step": 3730 |
| }, |
| { |
| "entropy": 0.46268435223028065, |
| "epoch": 1.664552384131753, |
| "grad_norm": 46.0, |
| "learning_rate": 1.3913333333333335e-05, |
| "loss": 7.3161, |
| "mean_token_accuracy": 0.8613630492240191, |
| "num_tokens": 24876091.0, |
| "step": 3740 |
| }, |
| { |
| "entropy": 0.4379832113161683, |
| "epoch": 1.6690035052578869, |
| "grad_norm": 46.75, |
| "learning_rate": 1.3891111111111114e-05, |
| "loss": 7.0153, |
| "mean_token_accuracy": 0.8646519504487514, |
| "num_tokens": 24940642.0, |
| "step": 3750 |
| }, |
| { |
| "entropy": 0.4273253384977579, |
| "epoch": 1.6734546263840204, |
| "grad_norm": 49.75, |
| "learning_rate": 1.386888888888889e-05, |
| "loss": 6.8384, |
| "mean_token_accuracy": 0.8686905398964881, |
| "num_tokens": 25009086.0, |
| "step": 3760 |
| }, |
| { |
| "entropy": 0.4892806939780712, |
| "epoch": 1.6779057475101542, |
| "grad_norm": 40.75, |
| "learning_rate": 1.3846666666666669e-05, |
| "loss": 7.8103, |
| "mean_token_accuracy": 0.8563035938888788, |
| "num_tokens": 25075466.0, |
| "step": 3770 |
| }, |
| { |
| "entropy": 0.4964268452487886, |
| "epoch": 1.6823568686362878, |
| "grad_norm": 52.0, |
| "learning_rate": 1.3824444444444445e-05, |
| "loss": 8.0125, |
| "mean_token_accuracy": 0.850185252726078, |
| "num_tokens": 25140113.0, |
| "step": 3780 |
| }, |
| { |
| "entropy": 0.4275729003828019, |
| "epoch": 1.6868079897624213, |
| "grad_norm": 55.5, |
| "learning_rate": 1.3802222222222224e-05, |
| "loss": 6.651, |
| "mean_token_accuracy": 0.8706098463386297, |
| "num_tokens": 25204256.0, |
| "step": 3790 |
| }, |
| { |
| "entropy": 0.4284579326398671, |
| "epoch": 1.691259110888555, |
| "grad_norm": 47.25, |
| "learning_rate": 1.378e-05, |
| "loss": 6.951, |
| "mean_token_accuracy": 0.8685608327388763, |
| "num_tokens": 25273806.0, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.691259110888555, |
| "eval_biology_entropy": 1.1295575432181357, |
| "eval_biology_loss": 1.346897840499878, |
| "eval_biology_mean_token_accuracy": 0.6743368053436279, |
| "eval_biology_num_tokens": 25273806.0, |
| "eval_biology_runtime": 34.5894, |
| "eval_biology_samples_per_second": 14.455, |
| "eval_biology_steps_per_second": 14.455, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.691259110888555, |
| "eval_chemistry_entropy": 0.5654874822199345, |
| "eval_chemistry_loss": 0.656886100769043, |
| "eval_chemistry_mean_token_accuracy": 0.8126588127613068, |
| "eval_chemistry_num_tokens": 25273806.0, |
| "eval_chemistry_runtime": 39.2363, |
| "eval_chemistry_samples_per_second": 12.743, |
| "eval_chemistry_steps_per_second": 12.743, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.691259110888555, |
| "eval_math_entropy": 0.6416800563335419, |
| "eval_math_loss": 0.881636381149292, |
| "eval_math_mean_token_accuracy": 0.7750789314508438, |
| "eval_math_num_tokens": 25273806.0, |
| "eval_math_runtime": 40.0292, |
| "eval_math_samples_per_second": 12.491, |
| "eval_math_steps_per_second": 12.491, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.691259110888555, |
| "eval_physics_entropy": 0.6213318961560726, |
| "eval_physics_loss": 0.7216943502426147, |
| "eval_physics_mean_token_accuracy": 0.8003399285674095, |
| "eval_physics_num_tokens": 25273806.0, |
| "eval_physics_runtime": 44.6644, |
| "eval_physics_samples_per_second": 11.195, |
| "eval_physics_steps_per_second": 11.195, |
| "step": 3800 |
| }, |
| { |
| "entropy": 0.44066512091085314, |
| "epoch": 1.6957102320146888, |
| "grad_norm": 48.25, |
| "learning_rate": 1.375777777777778e-05, |
| "loss": 6.8848, |
| "mean_token_accuracy": 0.8684013340622186, |
| "num_tokens": 25339482.0, |
| "step": 3810 |
| }, |
| { |
| "entropy": 0.4442510147579014, |
| "epoch": 1.7001613531408224, |
| "grad_norm": 44.5, |
| "learning_rate": 1.3735555555555557e-05, |
| "loss": 7.2251, |
| "mean_token_accuracy": 0.8653563387691975, |
| "num_tokens": 25408287.0, |
| "step": 3820 |
| }, |
| { |
| "entropy": 0.4577302812598646, |
| "epoch": 1.704612474266956, |
| "grad_norm": 49.5, |
| "learning_rate": 1.3713333333333335e-05, |
| "loss": 7.2148, |
| "mean_token_accuracy": 0.8641619574278593, |
| "num_tokens": 25468817.0, |
| "step": 3830 |
| }, |
| { |
| "entropy": 0.4357797254808247, |
| "epoch": 1.7090635953930895, |
| "grad_norm": 51.0, |
| "learning_rate": 1.3691111111111112e-05, |
| "loss": 7.1943, |
| "mean_token_accuracy": 0.8651979338377714, |
| "num_tokens": 25532863.0, |
| "step": 3840 |
| }, |
| { |
| "entropy": 0.47953540496528146, |
| "epoch": 1.7135147165192233, |
| "grad_norm": 54.5, |
| "learning_rate": 1.366888888888889e-05, |
| "loss": 7.5829, |
| "mean_token_accuracy": 0.8597917027771473, |
| "num_tokens": 25599547.0, |
| "step": 3850 |
| }, |
| { |
| "entropy": 0.4563746053725481, |
| "epoch": 1.717965837645357, |
| "grad_norm": 55.5, |
| "learning_rate": 1.3646666666666668e-05, |
| "loss": 7.4194, |
| "mean_token_accuracy": 0.8617495015263558, |
| "num_tokens": 25664044.0, |
| "step": 3860 |
| }, |
| { |
| "entropy": 0.4477690393105149, |
| "epoch": 1.7224169587714906, |
| "grad_norm": 47.25, |
| "learning_rate": 1.3624444444444445e-05, |
| "loss": 7.0262, |
| "mean_token_accuracy": 0.8666216030716896, |
| "num_tokens": 25729236.0, |
| "step": 3870 |
| }, |
| { |
| "entropy": 0.447828256059438, |
| "epoch": 1.7268680798976241, |
| "grad_norm": 46.0, |
| "learning_rate": 1.3602222222222223e-05, |
| "loss": 7.2553, |
| "mean_token_accuracy": 0.8636733230203391, |
| "num_tokens": 25795212.0, |
| "step": 3880 |
| }, |
| { |
| "entropy": 0.4681910085491836, |
| "epoch": 1.731319201023758, |
| "grad_norm": 50.75, |
| "learning_rate": 1.3580000000000002e-05, |
| "loss": 7.4223, |
| "mean_token_accuracy": 0.8596210706979036, |
| "num_tokens": 25862976.0, |
| "step": 3890 |
| }, |
| { |
| "entropy": 0.4230806278064847, |
| "epoch": 1.7357703221498915, |
| "grad_norm": 48.0, |
| "learning_rate": 1.3557777777777778e-05, |
| "loss": 6.8182, |
| "mean_token_accuracy": 0.8694212134927511, |
| "num_tokens": 25932472.0, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.7357703221498915, |
| "eval_biology_entropy": 1.106598300755024, |
| "eval_biology_loss": 1.3472992181777954, |
| "eval_biology_mean_token_accuracy": 0.6745275885462761, |
| "eval_biology_num_tokens": 25932472.0, |
| "eval_biology_runtime": 34.4611, |
| "eval_biology_samples_per_second": 14.509, |
| "eval_biology_steps_per_second": 14.509, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.7357703221498915, |
| "eval_chemistry_entropy": 0.5568717788755894, |
| "eval_chemistry_loss": 0.6545698046684265, |
| "eval_chemistry_mean_token_accuracy": 0.8137574672698975, |
| "eval_chemistry_num_tokens": 25932472.0, |
| "eval_chemistry_runtime": 39.1167, |
| "eval_chemistry_samples_per_second": 12.782, |
| "eval_chemistry_steps_per_second": 12.782, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.7357703221498915, |
| "eval_math_entropy": 0.6416476690471172, |
| "eval_math_loss": 0.8763158917427063, |
| "eval_math_mean_token_accuracy": 0.7766710118055343, |
| "eval_math_num_tokens": 25932472.0, |
| "eval_math_runtime": 39.9076, |
| "eval_math_samples_per_second": 12.529, |
| "eval_math_steps_per_second": 12.529, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.7357703221498915, |
| "eval_physics_entropy": 0.61889935323596, |
| "eval_physics_loss": 0.720883846282959, |
| "eval_physics_mean_token_accuracy": 0.8009107040762902, |
| "eval_physics_num_tokens": 25932472.0, |
| "eval_physics_runtime": 44.6348, |
| "eval_physics_samples_per_second": 11.202, |
| "eval_physics_steps_per_second": 11.202, |
| "step": 3900 |
| }, |
| { |
| "entropy": 0.44790563243441284, |
| "epoch": 1.7402214432760252, |
| "grad_norm": 67.5, |
| "learning_rate": 1.3535555555555557e-05, |
| "loss": 7.1714, |
| "mean_token_accuracy": 0.8675620764493942, |
| "num_tokens": 26000782.0, |
| "step": 3910 |
| }, |
| { |
| "entropy": 0.4111007122322917, |
| "epoch": 1.7446725644021588, |
| "grad_norm": 42.75, |
| "learning_rate": 1.3513333333333333e-05, |
| "loss": 6.4259, |
| "mean_token_accuracy": 0.876038047298789, |
| "num_tokens": 26066017.0, |
| "step": 3920 |
| }, |
| { |
| "entropy": 0.43985592303797605, |
| "epoch": 1.7491236855282923, |
| "grad_norm": 60.0, |
| "learning_rate": 1.3491111111111113e-05, |
| "loss": 7.2024, |
| "mean_token_accuracy": 0.8645997188985348, |
| "num_tokens": 26135900.0, |
| "step": 3930 |
| }, |
| { |
| "entropy": 0.43924570400267837, |
| "epoch": 1.753574806654426, |
| "grad_norm": 48.0, |
| "learning_rate": 1.3468888888888888e-05, |
| "loss": 6.8362, |
| "mean_token_accuracy": 0.8705701280385256, |
| "num_tokens": 26202278.0, |
| "step": 3940 |
| }, |
| { |
| "entropy": 0.4564872051589191, |
| "epoch": 1.7580259277805599, |
| "grad_norm": 41.0, |
| "learning_rate": 1.3446666666666668e-05, |
| "loss": 7.2583, |
| "mean_token_accuracy": 0.8637916352599859, |
| "num_tokens": 26267299.0, |
| "step": 3950 |
| }, |
| { |
| "entropy": 0.39730430524796245, |
| "epoch": 1.7624770489066934, |
| "grad_norm": 43.25, |
| "learning_rate": 1.3424444444444447e-05, |
| "loss": 6.3589, |
| "mean_token_accuracy": 0.8773230772465468, |
| "num_tokens": 26335089.0, |
| "step": 3960 |
| }, |
| { |
| "entropy": 0.43639370501041413, |
| "epoch": 1.766928170032827, |
| "grad_norm": 49.5, |
| "learning_rate": 1.3402222222222223e-05, |
| "loss": 7.0329, |
| "mean_token_accuracy": 0.8650453139096499, |
| "num_tokens": 26401675.0, |
| "step": 3970 |
| }, |
| { |
| "entropy": 0.42879500295966866, |
| "epoch": 1.7713792911589605, |
| "grad_norm": 44.5, |
| "learning_rate": 1.3380000000000002e-05, |
| "loss": 6.9526, |
| "mean_token_accuracy": 0.8689841691404581, |
| "num_tokens": 26468664.0, |
| "step": 3980 |
| }, |
| { |
| "entropy": 0.41847693556919696, |
| "epoch": 1.7758304122850943, |
| "grad_norm": 54.75, |
| "learning_rate": 1.3357777777777778e-05, |
| "loss": 6.6059, |
| "mean_token_accuracy": 0.8745091546326875, |
| "num_tokens": 26533513.0, |
| "step": 3990 |
| }, |
| { |
| "entropy": 0.4298943846486509, |
| "epoch": 1.780281533411228, |
| "grad_norm": 41.25, |
| "learning_rate": 1.3335555555555558e-05, |
| "loss": 6.9075, |
| "mean_token_accuracy": 0.8683625862002373, |
| "num_tokens": 26599191.0, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.780281533411228, |
| "eval_biology_entropy": 1.1074971594810485, |
| "eval_biology_loss": 1.3493775129318237, |
| "eval_biology_mean_token_accuracy": 0.6751004811525345, |
| "eval_biology_num_tokens": 26599191.0, |
| "eval_biology_runtime": 34.6487, |
| "eval_biology_samples_per_second": 14.431, |
| "eval_biology_steps_per_second": 14.431, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.780281533411228, |
| "eval_chemistry_entropy": 0.5616140718758106, |
| "eval_chemistry_loss": 0.6527396440505981, |
| "eval_chemistry_mean_token_accuracy": 0.8135238691568375, |
| "eval_chemistry_num_tokens": 26599191.0, |
| "eval_chemistry_runtime": 39.0296, |
| "eval_chemistry_samples_per_second": 12.811, |
| "eval_chemistry_steps_per_second": 12.811, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.780281533411228, |
| "eval_math_entropy": 0.6419181789457798, |
| "eval_math_loss": 0.8851102590560913, |
| "eval_math_mean_token_accuracy": 0.7748768546581268, |
| "eval_math_num_tokens": 26599191.0, |
| "eval_math_runtime": 39.9452, |
| "eval_math_samples_per_second": 12.517, |
| "eval_math_steps_per_second": 12.517, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.780281533411228, |
| "eval_physics_entropy": 0.623605739235878, |
| "eval_physics_loss": 0.7205914258956909, |
| "eval_physics_mean_token_accuracy": 0.8010671779513359, |
| "eval_physics_num_tokens": 26599191.0, |
| "eval_physics_runtime": 44.6033, |
| "eval_physics_samples_per_second": 11.21, |
| "eval_physics_steps_per_second": 11.21, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 10000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 1.783591898406408e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
