| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4451121126133645, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "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 |
| } |
| ], |
| "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": 4.450581354264347e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
