| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.4, |
| "eval_steps": 100, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.142920307815075, |
| "epoch": 0.016, |
| "grad_norm": 290.0, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 42.6658, |
| "mean_token_accuracy": 0.5620782226324081, |
| "num_tokens": 195524.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.148210159689188, |
| "epoch": 0.032, |
| "grad_norm": 239.0, |
| "learning_rate": 1.2666666666666669e-06, |
| "loss": 41.9984, |
| "mean_token_accuracy": 0.5613080382347106, |
| "num_tokens": 390903.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.1933260083198547, |
| "epoch": 0.048, |
| "grad_norm": 249.0, |
| "learning_rate": 1.9333333333333336e-06, |
| "loss": 40.6208, |
| "mean_token_accuracy": 0.5657517908141017, |
| "num_tokens": 589868.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.2957281917333603, |
| "epoch": 0.064, |
| "grad_norm": 139.0, |
| "learning_rate": 2.6e-06, |
| "loss": 37.9032, |
| "mean_token_accuracy": 0.5714796105399728, |
| "num_tokens": 791190.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.5075685508549213, |
| "epoch": 0.08, |
| "grad_norm": 94.0, |
| "learning_rate": 3.266666666666667e-06, |
| "loss": 35.7561, |
| "mean_token_accuracy": 0.5766569443047047, |
| "num_tokens": 989860.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.7984249681234359, |
| "epoch": 0.096, |
| "grad_norm": 50.75, |
| "learning_rate": 3.9333333333333335e-06, |
| "loss": 33.4379, |
| "mean_token_accuracy": 0.5814697606489062, |
| "num_tokens": 1181777.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.8387351341545581, |
| "epoch": 0.112, |
| "grad_norm": 43.0, |
| "learning_rate": 4.600000000000001e-06, |
| "loss": 30.4219, |
| "mean_token_accuracy": 0.5971228444948793, |
| "num_tokens": 1385513.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.7275233700871468, |
| "epoch": 0.128, |
| "grad_norm": 33.5, |
| "learning_rate": 5.2666666666666665e-06, |
| "loss": 28.4703, |
| "mean_token_accuracy": 0.6095364252105355, |
| "num_tokens": 1582368.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.7214979872107505, |
| "epoch": 0.144, |
| "grad_norm": 27.0, |
| "learning_rate": 5.933333333333335e-06, |
| "loss": 26.677, |
| "mean_token_accuracy": 0.6243448719382286, |
| "num_tokens": 1773764.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.6311134904623033, |
| "epoch": 0.16, |
| "grad_norm": 22.0, |
| "learning_rate": 6.600000000000001e-06, |
| "loss": 25.7683, |
| "mean_token_accuracy": 0.6301404371857643, |
| "num_tokens": 1970077.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_biology_entropy": 1.5580159120559693, |
| "eval_biology_loss": 1.5081593990325928, |
| "eval_biology_mean_token_accuracy": 0.6457349667549134, |
| "eval_biology_num_tokens": 1970077.0, |
| "eval_biology_runtime": 48.7413, |
| "eval_biology_samples_per_second": 10.258, |
| "eval_biology_steps_per_second": 2.565, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_chemistry_entropy": 1.206756212234497, |
| "eval_chemistry_loss": 1.1218774318695068, |
| "eval_chemistry_mean_token_accuracy": 0.7205783066749573, |
| "eval_chemistry_num_tokens": 1970077.0, |
| "eval_chemistry_runtime": 60.3159, |
| "eval_chemistry_samples_per_second": 8.29, |
| "eval_chemistry_steps_per_second": 2.072, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_math_entropy": 0.9672308325767517, |
| "eval_math_loss": 1.159799337387085, |
| "eval_math_mean_token_accuracy": 0.7189845342636109, |
| "eval_math_num_tokens": 1970077.0, |
| "eval_math_runtime": 61.8237, |
| "eval_math_samples_per_second": 8.088, |
| "eval_math_steps_per_second": 2.022, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_physics_entropy": 1.1670387201309205, |
| "eval_physics_loss": 1.1291608810424805, |
| "eval_physics_mean_token_accuracy": 0.7211072521209717, |
| "eval_physics_num_tokens": 1970077.0, |
| "eval_physics_runtime": 70.4586, |
| "eval_physics_samples_per_second": 7.096, |
| "eval_physics_steps_per_second": 1.774, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.5482715763151647, |
| "epoch": 0.176, |
| "grad_norm": 21.125, |
| "learning_rate": 7.266666666666668e-06, |
| "loss": 24.5868, |
| "mean_token_accuracy": 0.6385629490017891, |
| "num_tokens": 2168354.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.5266574397683144, |
| "epoch": 0.192, |
| "grad_norm": 22.875, |
| "learning_rate": 7.933333333333334e-06, |
| "loss": 24.2707, |
| "mean_token_accuracy": 0.6432460084557533, |
| "num_tokens": 2365822.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 1.5192069873213767, |
| "epoch": 0.208, |
| "grad_norm": 20.875, |
| "learning_rate": 8.6e-06, |
| "loss": 24.1355, |
| "mean_token_accuracy": 0.6436416517943144, |
| "num_tokens": 2558762.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.4698147468268872, |
| "epoch": 0.224, |
| "grad_norm": 20.125, |
| "learning_rate": 9.266666666666667e-06, |
| "loss": 23.5154, |
| "mean_token_accuracy": 0.6499760080128908, |
| "num_tokens": 2755347.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.4506230603903532, |
| "epoch": 0.24, |
| "grad_norm": 19.625, |
| "learning_rate": 9.933333333333334e-06, |
| "loss": 23.2013, |
| "mean_token_accuracy": 0.6523264441639185, |
| "num_tokens": 2947346.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.4590953961014748, |
| "epoch": 0.256, |
| "grad_norm": 18.5, |
| "learning_rate": 1.0600000000000002e-05, |
| "loss": 23.3227, |
| "mean_token_accuracy": 0.6508617259562015, |
| "num_tokens": 3139957.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 1.419396448880434, |
| "epoch": 0.272, |
| "grad_norm": 19.75, |
| "learning_rate": 1.1266666666666668e-05, |
| "loss": 22.7352, |
| "mean_token_accuracy": 0.6572458431124687, |
| "num_tokens": 3335951.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 1.4005608204752207, |
| "epoch": 0.288, |
| "grad_norm": 19.75, |
| "learning_rate": 1.1933333333333335e-05, |
| "loss": 22.3969, |
| "mean_token_accuracy": 0.6585959013551473, |
| "num_tokens": 3539731.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 1.391934547200799, |
| "epoch": 0.304, |
| "grad_norm": 18.75, |
| "learning_rate": 1.2600000000000001e-05, |
| "loss": 22.31, |
| "mean_token_accuracy": 0.6621056370437145, |
| "num_tokens": 3733488.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 1.4028674490749835, |
| "epoch": 0.32, |
| "grad_norm": 22.25, |
| "learning_rate": 1.3266666666666668e-05, |
| "loss": 22.5559, |
| "mean_token_accuracy": 0.6576981086283922, |
| "num_tokens": 3920545.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_biology_entropy": 1.3209806289672852, |
| "eval_biology_loss": 1.338399887084961, |
| "eval_biology_mean_token_accuracy": 0.6720403518676757, |
| "eval_biology_num_tokens": 3920545.0, |
| "eval_biology_runtime": 48.5853, |
| "eval_biology_samples_per_second": 10.291, |
| "eval_biology_steps_per_second": 2.573, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_chemistry_entropy": 1.0033348879814148, |
| "eval_chemistry_loss": 0.9935092926025391, |
| "eval_chemistry_mean_token_accuracy": 0.7448974308967591, |
| "eval_chemistry_num_tokens": 3920545.0, |
| "eval_chemistry_runtime": 60.24, |
| "eval_chemistry_samples_per_second": 8.3, |
| "eval_chemistry_steps_per_second": 2.075, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_math_entropy": 0.8341804294586181, |
| "eval_math_loss": 1.0635857582092285, |
| "eval_math_mean_token_accuracy": 0.7432106451988221, |
| "eval_math_num_tokens": 3920545.0, |
| "eval_math_runtime": 61.8174, |
| "eval_math_samples_per_second": 8.088, |
| "eval_math_steps_per_second": 2.022, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_physics_entropy": 0.9652358031272888, |
| "eval_physics_loss": 0.9950281977653503, |
| "eval_physics_mean_token_accuracy": 0.7510108857154846, |
| "eval_physics_num_tokens": 3920545.0, |
| "eval_physics_runtime": 70.411, |
| "eval_physics_samples_per_second": 7.101, |
| "eval_physics_steps_per_second": 1.775, |
| "step": 200 |
| }, |
| { |
| "entropy": 1.3548175282776356, |
| "epoch": 0.336, |
| "grad_norm": 19.625, |
| "learning_rate": 1.3933333333333334e-05, |
| "loss": 21.7763, |
| "mean_token_accuracy": 0.6656343434005976, |
| "num_tokens": 4114077.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 1.3656601022928954, |
| "epoch": 0.352, |
| "grad_norm": 20.625, |
| "learning_rate": 1.46e-05, |
| "loss": 22.0972, |
| "mean_token_accuracy": 0.6638848338276148, |
| "num_tokens": 4306949.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 1.3525194190442562, |
| "epoch": 0.368, |
| "grad_norm": 18.125, |
| "learning_rate": 1.5266666666666667e-05, |
| "loss": 21.7293, |
| "mean_token_accuracy": 0.6680811226367951, |
| "num_tokens": 4504001.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 1.3454820621758699, |
| "epoch": 0.384, |
| "grad_norm": 21.25, |
| "learning_rate": 1.5933333333333336e-05, |
| "loss": 21.7032, |
| "mean_token_accuracy": 0.6671383358538151, |
| "num_tokens": 4693812.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 1.3525703553110362, |
| "epoch": 0.4, |
| "grad_norm": 17.5, |
| "learning_rate": 1.66e-05, |
| "loss": 21.7856, |
| "mean_token_accuracy": 0.666401931643486, |
| "num_tokens": 4887094.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 1.351718918606639, |
| "epoch": 0.416, |
| "grad_norm": 19.0, |
| "learning_rate": 1.726666666666667e-05, |
| "loss": 21.9058, |
| "mean_token_accuracy": 0.6651136819273233, |
| "num_tokens": 5085369.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 1.3526419658213853, |
| "epoch": 0.432, |
| "grad_norm": 20.875, |
| "learning_rate": 1.7933333333333333e-05, |
| "loss": 21.7813, |
| "mean_token_accuracy": 0.6668458927422762, |
| "num_tokens": 5271275.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 1.3480545241385697, |
| "epoch": 0.448, |
| "grad_norm": 22.875, |
| "learning_rate": 1.86e-05, |
| "loss": 21.627, |
| "mean_token_accuracy": 0.6677324704825878, |
| "num_tokens": 5460559.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 1.301166184991598, |
| "epoch": 0.464, |
| "grad_norm": 21.25, |
| "learning_rate": 1.926666666666667e-05, |
| "loss": 20.889, |
| "mean_token_accuracy": 0.676617132872343, |
| "num_tokens": 5653809.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 1.318466317281127, |
| "epoch": 0.48, |
| "grad_norm": 17.125, |
| "learning_rate": 1.9933333333333334e-05, |
| "loss": 21.2936, |
| "mean_token_accuracy": 0.6712827417999506, |
| "num_tokens": 5850176.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_biology_entropy": 1.2827796216011047, |
| "eval_biology_loss": 1.275201678276062, |
| "eval_biology_mean_token_accuracy": 0.6830832781791687, |
| "eval_biology_num_tokens": 5850176.0, |
| "eval_biology_runtime": 48.4915, |
| "eval_biology_samples_per_second": 10.311, |
| "eval_biology_steps_per_second": 2.578, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_chemistry_entropy": 0.983495129108429, |
| "eval_chemistry_loss": 0.9488818645477295, |
| "eval_chemistry_mean_token_accuracy": 0.7523409638404847, |
| "eval_chemistry_num_tokens": 5850176.0, |
| "eval_chemistry_runtime": 60.1707, |
| "eval_chemistry_samples_per_second": 8.31, |
| "eval_chemistry_steps_per_second": 2.077, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_math_entropy": 0.8216862387657166, |
| "eval_math_loss": 1.0297818183898926, |
| "eval_math_mean_token_accuracy": 0.7488151121139527, |
| "eval_math_num_tokens": 5850176.0, |
| "eval_math_runtime": 61.6905, |
| "eval_math_samples_per_second": 8.105, |
| "eval_math_steps_per_second": 2.026, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_physics_entropy": 0.9433758721351624, |
| "eval_physics_loss": 0.9520999193191528, |
| "eval_physics_mean_token_accuracy": 0.7585058889389038, |
| "eval_physics_num_tokens": 5850176.0, |
| "eval_physics_runtime": 70.301, |
| "eval_physics_samples_per_second": 7.112, |
| "eval_physics_steps_per_second": 1.778, |
| "step": 300 |
| }, |
| { |
| "entropy": 1.2579400472342968, |
| "epoch": 0.496, |
| "grad_norm": 17.75, |
| "learning_rate": 1.9933333333333334e-05, |
| "loss": 20.2011, |
| "mean_token_accuracy": 0.6842056062072516, |
| "num_tokens": 6046503.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 1.3082518883049488, |
| "epoch": 0.512, |
| "grad_norm": 18.125, |
| "learning_rate": 1.985925925925926e-05, |
| "loss": 21.0658, |
| "mean_token_accuracy": 0.6749501373618841, |
| "num_tokens": 6240456.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 1.3003981616348028, |
| "epoch": 0.528, |
| "grad_norm": 18.125, |
| "learning_rate": 1.9785185185185187e-05, |
| "loss": 20.9809, |
| "mean_token_accuracy": 0.6757604543119669, |
| "num_tokens": 6430555.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 1.2986273631453513, |
| "epoch": 0.544, |
| "grad_norm": 17.0, |
| "learning_rate": 1.971111111111111e-05, |
| "loss": 20.8809, |
| "mean_token_accuracy": 0.6782271713018417, |
| "num_tokens": 6626006.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 1.284830729290843, |
| "epoch": 0.56, |
| "grad_norm": 17.25, |
| "learning_rate": 1.963703703703704e-05, |
| "loss": 20.8197, |
| "mean_token_accuracy": 0.6767117112874985, |
| "num_tokens": 6820754.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 1.2683125745505095, |
| "epoch": 0.576, |
| "grad_norm": 17.0, |
| "learning_rate": 1.9562962962962964e-05, |
| "loss": 20.4541, |
| "mean_token_accuracy": 0.6809794403612613, |
| "num_tokens": 7021844.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 1.2863252360373736, |
| "epoch": 0.592, |
| "grad_norm": 18.875, |
| "learning_rate": 1.948888888888889e-05, |
| "loss": 20.8043, |
| "mean_token_accuracy": 0.676701345667243, |
| "num_tokens": 7213951.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 1.2630502216517925, |
| "epoch": 0.608, |
| "grad_norm": 18.75, |
| "learning_rate": 1.9414814814814817e-05, |
| "loss": 20.4041, |
| "mean_token_accuracy": 0.6803740747272968, |
| "num_tokens": 7416773.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 1.2804703898727894, |
| "epoch": 0.624, |
| "grad_norm": 19.25, |
| "learning_rate": 1.9340740740740743e-05, |
| "loss": 20.6218, |
| "mean_token_accuracy": 0.6788272958248853, |
| "num_tokens": 7612843.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 1.2843346055597067, |
| "epoch": 0.64, |
| "grad_norm": 18.0, |
| "learning_rate": 1.926666666666667e-05, |
| "loss": 20.7171, |
| "mean_token_accuracy": 0.6782444745302201, |
| "num_tokens": 7801633.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_biology_entropy": 1.226506398677826, |
| "eval_biology_loss": 1.2382104396820068, |
| "eval_biology_mean_token_accuracy": 0.6894095778465271, |
| "eval_biology_num_tokens": 7801633.0, |
| "eval_biology_runtime": 48.5507, |
| "eval_biology_samples_per_second": 10.299, |
| "eval_biology_steps_per_second": 2.575, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_chemistry_entropy": 0.9317227191925049, |
| "eval_chemistry_loss": 0.9207452535629272, |
| "eval_chemistry_mean_token_accuracy": 0.7581370029449462, |
| "eval_chemistry_num_tokens": 7801633.0, |
| "eval_chemistry_runtime": 60.2113, |
| "eval_chemistry_samples_per_second": 8.304, |
| "eval_chemistry_steps_per_second": 2.076, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_math_entropy": 0.7863595089912414, |
| "eval_math_loss": 1.010460376739502, |
| "eval_math_mean_token_accuracy": 0.7535392093658447, |
| "eval_math_num_tokens": 7801633.0, |
| "eval_math_runtime": 61.807, |
| "eval_math_samples_per_second": 8.09, |
| "eval_math_steps_per_second": 2.022, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_physics_entropy": 0.8958085932731629, |
| "eval_physics_loss": 0.9257401823997498, |
| "eval_physics_mean_token_accuracy": 0.7637984156608582, |
| "eval_physics_num_tokens": 7801633.0, |
| "eval_physics_runtime": 70.3663, |
| "eval_physics_samples_per_second": 7.106, |
| "eval_physics_steps_per_second": 1.776, |
| "step": 400 |
| }, |
| { |
| "entropy": 1.278659427165985, |
| "epoch": 0.656, |
| "grad_norm": 18.25, |
| "learning_rate": 1.9192592592592593e-05, |
| "loss": 20.6682, |
| "mean_token_accuracy": 0.6772829819470644, |
| "num_tokens": 7995843.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 1.2931427203118802, |
| "epoch": 0.672, |
| "grad_norm": 18.625, |
| "learning_rate": 1.911851851851852e-05, |
| "loss": 20.8656, |
| "mean_token_accuracy": 0.6753748003393412, |
| "num_tokens": 8183103.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 1.2739692747592926, |
| "epoch": 0.688, |
| "grad_norm": 16.75, |
| "learning_rate": 1.9044444444444446e-05, |
| "loss": 20.5407, |
| "mean_token_accuracy": 0.6812681049108505, |
| "num_tokens": 8385976.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 1.2659825466573238, |
| "epoch": 0.704, |
| "grad_norm": 16.25, |
| "learning_rate": 1.8970370370370372e-05, |
| "loss": 20.4243, |
| "mean_token_accuracy": 0.6820976916700602, |
| "num_tokens": 8578431.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 1.220404140278697, |
| "epoch": 0.72, |
| "grad_norm": 16.75, |
| "learning_rate": 1.8896296296296295e-05, |
| "loss": 19.6546, |
| "mean_token_accuracy": 0.6908745598047972, |
| "num_tokens": 8781342.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 1.2406103231012822, |
| "epoch": 0.736, |
| "grad_norm": 16.75, |
| "learning_rate": 1.8822222222222225e-05, |
| "loss": 19.9745, |
| "mean_token_accuracy": 0.6853331789374352, |
| "num_tokens": 8977918.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 1.2618801843374967, |
| "epoch": 0.752, |
| "grad_norm": 17.125, |
| "learning_rate": 1.874814814814815e-05, |
| "loss": 20.4041, |
| "mean_token_accuracy": 0.6825968738645315, |
| "num_tokens": 9169322.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 1.2232345014810562, |
| "epoch": 0.768, |
| "grad_norm": 19.25, |
| "learning_rate": 1.8674074074074075e-05, |
| "loss": 19.7045, |
| "mean_token_accuracy": 0.6888250291347504, |
| "num_tokens": 9368141.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 1.25159954726696, |
| "epoch": 0.784, |
| "grad_norm": 18.25, |
| "learning_rate": 1.86e-05, |
| "loss": 20.2036, |
| "mean_token_accuracy": 0.6849453710019588, |
| "num_tokens": 9565236.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 1.264250884205103, |
| "epoch": 0.8, |
| "grad_norm": 19.25, |
| "learning_rate": 1.8525925925925928e-05, |
| "loss": 20.5299, |
| "mean_token_accuracy": 0.6811827480792999, |
| "num_tokens": 9761227.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_biology_entropy": 1.2163097896575927, |
| "eval_biology_loss": 1.2177292108535767, |
| "eval_biology_mean_token_accuracy": 0.6932459664344788, |
| "eval_biology_num_tokens": 9761227.0, |
| "eval_biology_runtime": 48.5438, |
| "eval_biology_samples_per_second": 10.3, |
| "eval_biology_steps_per_second": 2.575, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_chemistry_entropy": 0.9239063205718994, |
| "eval_chemistry_loss": 0.9047155380249023, |
| "eval_chemistry_mean_token_accuracy": 0.761792631149292, |
| "eval_chemistry_num_tokens": 9761227.0, |
| "eval_chemistry_runtime": 59.9546, |
| "eval_chemistry_samples_per_second": 8.34, |
| "eval_chemistry_steps_per_second": 2.085, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_math_entropy": 0.7864464523792267, |
| "eval_math_loss": 0.9939978122711182, |
| "eval_math_mean_token_accuracy": 0.7574145245552063, |
| "eval_math_num_tokens": 9761227.0, |
| "eval_math_runtime": 61.7812, |
| "eval_math_samples_per_second": 8.093, |
| "eval_math_steps_per_second": 2.023, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_physics_entropy": 0.889360978603363, |
| "eval_physics_loss": 0.9096766710281372, |
| "eval_physics_mean_token_accuracy": 0.7674052910804748, |
| "eval_physics_num_tokens": 9761227.0, |
| "eval_physics_runtime": 70.5356, |
| "eval_physics_samples_per_second": 7.089, |
| "eval_physics_steps_per_second": 1.772, |
| "step": 500 |
| }, |
| { |
| "entropy": 1.2362793002277612, |
| "epoch": 0.816, |
| "grad_norm": 19.625, |
| "learning_rate": 1.8451851851851855e-05, |
| "loss": 19.8133, |
| "mean_token_accuracy": 0.6863504596054554, |
| "num_tokens": 9958727.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 1.2254926670342683, |
| "epoch": 0.832, |
| "grad_norm": 17.0, |
| "learning_rate": 1.8377777777777778e-05, |
| "loss": 19.8307, |
| "mean_token_accuracy": 0.6866675779223442, |
| "num_tokens": 10155771.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 1.2238412775099277, |
| "epoch": 0.848, |
| "grad_norm": 18.75, |
| "learning_rate": 1.8303703703703704e-05, |
| "loss": 19.687, |
| "mean_token_accuracy": 0.6897137116640806, |
| "num_tokens": 10357721.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 1.2536957442760468, |
| "epoch": 0.864, |
| "grad_norm": 17.125, |
| "learning_rate": 1.822962962962963e-05, |
| "loss": 20.1565, |
| "mean_token_accuracy": 0.6850291140377521, |
| "num_tokens": 10552495.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 1.231699001789093, |
| "epoch": 0.88, |
| "grad_norm": 18.25, |
| "learning_rate": 1.8155555555555557e-05, |
| "loss": 19.8536, |
| "mean_token_accuracy": 0.6891282081604004, |
| "num_tokens": 10748749.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 1.2470501396805047, |
| "epoch": 0.896, |
| "grad_norm": 18.0, |
| "learning_rate": 1.8081481481481484e-05, |
| "loss": 20.1706, |
| "mean_token_accuracy": 0.6856059569865465, |
| "num_tokens": 10943319.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 1.2307742841541767, |
| "epoch": 0.912, |
| "grad_norm": 18.25, |
| "learning_rate": 1.800740740740741e-05, |
| "loss": 19.9062, |
| "mean_token_accuracy": 0.6885740786790848, |
| "num_tokens": 11136935.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 1.2445739306509496, |
| "epoch": 0.928, |
| "grad_norm": 18.0, |
| "learning_rate": 1.7933333333333333e-05, |
| "loss": 20.0979, |
| "mean_token_accuracy": 0.6851089850068093, |
| "num_tokens": 11331098.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 1.2021468229591847, |
| "epoch": 0.944, |
| "grad_norm": 15.875, |
| "learning_rate": 1.785925925925926e-05, |
| "loss": 19.4077, |
| "mean_token_accuracy": 0.6915138956159353, |
| "num_tokens": 11530550.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 1.226809823140502, |
| "epoch": 0.96, |
| "grad_norm": 19.625, |
| "learning_rate": 1.7785185185185186e-05, |
| "loss": 19.8062, |
| "mean_token_accuracy": 0.6897286407649517, |
| "num_tokens": 11729645.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_biology_entropy": 1.1845180039405823, |
| "eval_biology_loss": 1.203829050064087, |
| "eval_biology_mean_token_accuracy": 0.6961685500144958, |
| "eval_biology_num_tokens": 11729645.0, |
| "eval_biology_runtime": 48.6169, |
| "eval_biology_samples_per_second": 10.284, |
| "eval_biology_steps_per_second": 2.571, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_chemistry_entropy": 0.90015394115448, |
| "eval_chemistry_loss": 0.8946329355239868, |
| "eval_chemistry_mean_token_accuracy": 0.7635614371299744, |
| "eval_chemistry_num_tokens": 11729645.0, |
| "eval_chemistry_runtime": 60.2919, |
| "eval_chemistry_samples_per_second": 8.293, |
| "eval_chemistry_steps_per_second": 2.073, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_math_entropy": 0.7684455904960632, |
| "eval_math_loss": 0.9900413751602173, |
| "eval_math_mean_token_accuracy": 0.7588200316429138, |
| "eval_math_num_tokens": 11729645.0, |
| "eval_math_runtime": 61.8301, |
| "eval_math_samples_per_second": 8.087, |
| "eval_math_steps_per_second": 2.022, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_physics_entropy": 0.8686938014030456, |
| "eval_physics_loss": 0.9008635878562927, |
| "eval_physics_mean_token_accuracy": 0.7692377109527588, |
| "eval_physics_num_tokens": 11729645.0, |
| "eval_physics_runtime": 70.4349, |
| "eval_physics_samples_per_second": 7.099, |
| "eval_physics_steps_per_second": 1.775, |
| "step": 600 |
| }, |
| { |
| "entropy": 1.2100978799164295, |
| "epoch": 0.976, |
| "grad_norm": 18.0, |
| "learning_rate": 1.7711111111111113e-05, |
| "loss": 19.47, |
| "mean_token_accuracy": 0.6918121088296175, |
| "num_tokens": 11924644.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 1.2226450834423304, |
| "epoch": 0.992, |
| "grad_norm": 16.625, |
| "learning_rate": 1.763703703703704e-05, |
| "loss": 19.8416, |
| "mean_token_accuracy": 0.688375661149621, |
| "num_tokens": 12123059.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 1.2316548496484756, |
| "epoch": 1.008, |
| "grad_norm": 16.875, |
| "learning_rate": 1.7562962962962962e-05, |
| "loss": 19.6116, |
| "mean_token_accuracy": 0.6919524800032377, |
| "num_tokens": 12319366.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 1.1779099617153406, |
| "epoch": 1.024, |
| "grad_norm": 19.0, |
| "learning_rate": 1.7488888888888892e-05, |
| "loss": 18.9763, |
| "mean_token_accuracy": 0.6978646669536829, |
| "num_tokens": 12524183.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 1.2152834441512823, |
| "epoch": 1.04, |
| "grad_norm": 17.75, |
| "learning_rate": 1.7414814814814815e-05, |
| "loss": 19.6247, |
| "mean_token_accuracy": 0.6903412740677595, |
| "num_tokens": 12718593.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 1.1799768891185523, |
| "epoch": 1.056, |
| "grad_norm": 18.625, |
| "learning_rate": 1.7340740740740742e-05, |
| "loss": 19.0432, |
| "mean_token_accuracy": 0.6986244544386864, |
| "num_tokens": 12917803.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 1.2108702428638936, |
| "epoch": 1.072, |
| "grad_norm": 19.125, |
| "learning_rate": 1.726666666666667e-05, |
| "loss": 19.4166, |
| "mean_token_accuracy": 0.6927186574786901, |
| "num_tokens": 13105826.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 1.1979756511747837, |
| "epoch": 1.088, |
| "grad_norm": 18.875, |
| "learning_rate": 1.7192592592592595e-05, |
| "loss": 19.2605, |
| "mean_token_accuracy": 0.6957505799829959, |
| "num_tokens": 13298619.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 1.192365935444832, |
| "epoch": 1.104, |
| "grad_norm": 17.875, |
| "learning_rate": 1.711851851851852e-05, |
| "loss": 19.2461, |
| "mean_token_accuracy": 0.695810866355896, |
| "num_tokens": 13491486.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 1.212946466356516, |
| "epoch": 1.12, |
| "grad_norm": 19.25, |
| "learning_rate": 1.7044444444444445e-05, |
| "loss": 19.5004, |
| "mean_token_accuracy": 0.692466252297163, |
| "num_tokens": 13674663.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_biology_entropy": 1.1571769905090332, |
| "eval_biology_loss": 1.1946450471878052, |
| "eval_biology_mean_token_accuracy": 0.6972691407203674, |
| "eval_biology_num_tokens": 13674663.0, |
| "eval_biology_runtime": 48.6729, |
| "eval_biology_samples_per_second": 10.273, |
| "eval_biology_steps_per_second": 2.568, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_chemistry_entropy": 0.8766862626075744, |
| "eval_chemistry_loss": 0.8891168236732483, |
| "eval_chemistry_mean_token_accuracy": 0.7645404329299926, |
| "eval_chemistry_num_tokens": 13674663.0, |
| "eval_chemistry_runtime": 60.3334, |
| "eval_chemistry_samples_per_second": 8.287, |
| "eval_chemistry_steps_per_second": 2.072, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_math_entropy": 0.7603865313529968, |
| "eval_math_loss": 0.9834137558937073, |
| "eval_math_mean_token_accuracy": 0.7596666264533997, |
| "eval_math_num_tokens": 13674663.0, |
| "eval_math_runtime": 61.8146, |
| "eval_math_samples_per_second": 8.089, |
| "eval_math_steps_per_second": 2.022, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_physics_entropy": 0.850571988105774, |
| "eval_physics_loss": 0.8937918543815613, |
| "eval_physics_mean_token_accuracy": 0.7703958468437195, |
| "eval_physics_num_tokens": 13674663.0, |
| "eval_physics_runtime": 70.4674, |
| "eval_physics_samples_per_second": 7.095, |
| "eval_physics_steps_per_second": 1.774, |
| "step": 700 |
| }, |
| { |
| "entropy": 1.1909121543169021, |
| "epoch": 1.1360000000000001, |
| "grad_norm": 18.875, |
| "learning_rate": 1.697037037037037e-05, |
| "loss": 19.2462, |
| "mean_token_accuracy": 0.6955781776458025, |
| "num_tokens": 13869134.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 1.1682380847632885, |
| "epoch": 1.152, |
| "grad_norm": 16.75, |
| "learning_rate": 1.6896296296296298e-05, |
| "loss": 18.8229, |
| "mean_token_accuracy": 0.6991135813295841, |
| "num_tokens": 14078365.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 1.1939557407051324, |
| "epoch": 1.168, |
| "grad_norm": 16.875, |
| "learning_rate": 1.6822222222222224e-05, |
| "loss": 19.1346, |
| "mean_token_accuracy": 0.6960698150098323, |
| "num_tokens": 14266831.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 1.180869185552001, |
| "epoch": 1.184, |
| "grad_norm": 18.25, |
| "learning_rate": 1.6748148148148147e-05, |
| "loss": 19.2654, |
| "mean_token_accuracy": 0.6941378649324179, |
| "num_tokens": 14465660.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 1.1937656667083503, |
| "epoch": 1.2, |
| "grad_norm": 18.25, |
| "learning_rate": 1.6674074074074077e-05, |
| "loss": 19.0305, |
| "mean_token_accuracy": 0.6964295905083417, |
| "num_tokens": 14653228.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 1.1589823190122843, |
| "epoch": 1.216, |
| "grad_norm": 17.875, |
| "learning_rate": 1.66e-05, |
| "loss": 18.6048, |
| "mean_token_accuracy": 0.7018654596060514, |
| "num_tokens": 14857782.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 1.1703605465590954, |
| "epoch": 1.232, |
| "grad_norm": 17.375, |
| "learning_rate": 1.6525925925925927e-05, |
| "loss": 18.8831, |
| "mean_token_accuracy": 0.7015001580119133, |
| "num_tokens": 15047356.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 1.1772115517407655, |
| "epoch": 1.248, |
| "grad_norm": 17.875, |
| "learning_rate": 1.6451851851851853e-05, |
| "loss": 19.0432, |
| "mean_token_accuracy": 0.6959997840225697, |
| "num_tokens": 15241098.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 1.196473068371415, |
| "epoch": 1.264, |
| "grad_norm": 16.375, |
| "learning_rate": 1.637777777777778e-05, |
| "loss": 19.1591, |
| "mean_token_accuracy": 0.6967897292226553, |
| "num_tokens": 15437657.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 1.2014197081327438, |
| "epoch": 1.28, |
| "grad_norm": 19.125, |
| "learning_rate": 1.6303703703703706e-05, |
| "loss": 19.4409, |
| "mean_token_accuracy": 0.6926549930125475, |
| "num_tokens": 15630795.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_biology_entropy": 1.134603425502777, |
| "eval_biology_loss": 1.1884372234344482, |
| "eval_biology_mean_token_accuracy": 0.6986491298675537, |
| "eval_biology_num_tokens": 15630795.0, |
| "eval_biology_runtime": 48.6306, |
| "eval_biology_samples_per_second": 10.282, |
| "eval_biology_steps_per_second": 2.57, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_chemistry_entropy": 0.8623910093307495, |
| "eval_chemistry_loss": 0.885444700717926, |
| "eval_chemistry_mean_token_accuracy": 0.7653528556823731, |
| "eval_chemistry_num_tokens": 15630795.0, |
| "eval_chemistry_runtime": 60.3508, |
| "eval_chemistry_samples_per_second": 8.285, |
| "eval_chemistry_steps_per_second": 2.071, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_math_entropy": 0.7589023416042328, |
| "eval_math_loss": 0.983073353767395, |
| "eval_math_mean_token_accuracy": 0.7593517408370972, |
| "eval_math_num_tokens": 15630795.0, |
| "eval_math_runtime": 61.9026, |
| "eval_math_samples_per_second": 8.077, |
| "eval_math_steps_per_second": 2.019, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_physics_entropy": 0.84130739736557, |
| "eval_physics_loss": 0.8907755613327026, |
| "eval_physics_mean_token_accuracy": 0.771062777519226, |
| "eval_physics_num_tokens": 15630795.0, |
| "eval_physics_runtime": 70.5226, |
| "eval_physics_samples_per_second": 7.09, |
| "eval_physics_steps_per_second": 1.772, |
| "step": 800 |
| }, |
| { |
| "entropy": 1.2085642520338298, |
| "epoch": 1.296, |
| "grad_norm": 17.375, |
| "learning_rate": 1.622962962962963e-05, |
| "loss": 19.3831, |
| "mean_token_accuracy": 0.6933640763163567, |
| "num_tokens": 15827105.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 1.1861349143087865, |
| "epoch": 1.312, |
| "grad_norm": 18.75, |
| "learning_rate": 1.6155555555555556e-05, |
| "loss": 19.3103, |
| "mean_token_accuracy": 0.694928414747119, |
| "num_tokens": 16019645.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 1.195632776618004, |
| "epoch": 1.328, |
| "grad_norm": 18.5, |
| "learning_rate": 1.6081481481481482e-05, |
| "loss": 19.3068, |
| "mean_token_accuracy": 0.6934712298214436, |
| "num_tokens": 16221726.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 1.1725192748010158, |
| "epoch": 1.3439999999999999, |
| "grad_norm": 17.0, |
| "learning_rate": 1.600740740740741e-05, |
| "loss": 18.7963, |
| "mean_token_accuracy": 0.700145885720849, |
| "num_tokens": 16427594.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 1.179823150858283, |
| "epoch": 1.3599999999999999, |
| "grad_norm": 18.75, |
| "learning_rate": 1.5933333333333336e-05, |
| "loss": 19.1154, |
| "mean_token_accuracy": 0.6961398232728243, |
| "num_tokens": 16621605.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 1.2228495314717294, |
| "epoch": 1.376, |
| "grad_norm": 19.5, |
| "learning_rate": 1.5859259259259262e-05, |
| "loss": 19.6627, |
| "mean_token_accuracy": 0.6894211061298847, |
| "num_tokens": 16813444.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 1.19021125882864, |
| "epoch": 1.392, |
| "grad_norm": 17.5, |
| "learning_rate": 1.5785185185185185e-05, |
| "loss": 19.2411, |
| "mean_token_accuracy": 0.6957099426537752, |
| "num_tokens": 17006509.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 1.184871331602335, |
| "epoch": 1.408, |
| "grad_norm": 15.4375, |
| "learning_rate": 1.571111111111111e-05, |
| "loss": 18.9785, |
| "mean_token_accuracy": 0.6971315786242485, |
| "num_tokens": 17197870.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 1.1884775411337614, |
| "epoch": 1.424, |
| "grad_norm": 17.25, |
| "learning_rate": 1.5637037037037038e-05, |
| "loss": 19.1289, |
| "mean_token_accuracy": 0.697301234304905, |
| "num_tokens": 17394390.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 1.1825116220861673, |
| "epoch": 1.44, |
| "grad_norm": 20.75, |
| "learning_rate": 1.5562962962962965e-05, |
| "loss": 19.1266, |
| "mean_token_accuracy": 0.6968252252787351, |
| "num_tokens": 17587777.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_biology_entropy": 1.1672434105873108, |
| "eval_biology_loss": 1.1815813779830933, |
| "eval_biology_mean_token_accuracy": 0.7003293070793152, |
| "eval_biology_num_tokens": 17587777.0, |
| "eval_biology_runtime": 48.6205, |
| "eval_biology_samples_per_second": 10.284, |
| "eval_biology_steps_per_second": 2.571, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_chemistry_entropy": 0.8869817838668823, |
| "eval_chemistry_loss": 0.8829970955848694, |
| "eval_chemistry_mean_token_accuracy": 0.7656374487876892, |
| "eval_chemistry_num_tokens": 17587777.0, |
| "eval_chemistry_runtime": 60.3339, |
| "eval_chemistry_samples_per_second": 8.287, |
| "eval_chemistry_steps_per_second": 2.072, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_math_entropy": 0.7674483435153961, |
| "eval_math_loss": 0.9792445302009583, |
| "eval_math_mean_token_accuracy": 0.7597224740982056, |
| "eval_math_num_tokens": 17587777.0, |
| "eval_math_runtime": 61.8239, |
| "eval_math_samples_per_second": 8.087, |
| "eval_math_steps_per_second": 2.022, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_physics_entropy": 0.8621900615692139, |
| "eval_physics_loss": 0.8884776830673218, |
| "eval_physics_mean_token_accuracy": 0.7715646696090698, |
| "eval_physics_num_tokens": 17587777.0, |
| "eval_physics_runtime": 70.446, |
| "eval_physics_samples_per_second": 7.098, |
| "eval_physics_steps_per_second": 1.774, |
| "step": 900 |
| }, |
| { |
| "entropy": 1.1818725422024727, |
| "epoch": 1.456, |
| "grad_norm": 18.25, |
| "learning_rate": 1.548888888888889e-05, |
| "loss": 19.032, |
| "mean_token_accuracy": 0.698200449720025, |
| "num_tokens": 17788456.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 1.1769807077944279, |
| "epoch": 1.472, |
| "grad_norm": 16.0, |
| "learning_rate": 1.5414814814814814e-05, |
| "loss": 18.8791, |
| "mean_token_accuracy": 0.7008779179304838, |
| "num_tokens": 17984063.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 1.1641013238579034, |
| "epoch": 1.488, |
| "grad_norm": 18.5, |
| "learning_rate": 1.5340740740740744e-05, |
| "loss": 18.9913, |
| "mean_token_accuracy": 0.6998269848525525, |
| "num_tokens": 18175640.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 1.1960251219570637, |
| "epoch": 1.504, |
| "grad_norm": 17.0, |
| "learning_rate": 1.5266666666666667e-05, |
| "loss": 19.2076, |
| "mean_token_accuracy": 0.696322177350521, |
| "num_tokens": 18367857.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 1.1745740845799446, |
| "epoch": 1.52, |
| "grad_norm": 16.875, |
| "learning_rate": 1.5192592592592594e-05, |
| "loss": 19.0307, |
| "mean_token_accuracy": 0.6969408400356769, |
| "num_tokens": 18569146.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 1.2008745949715376, |
| "epoch": 1.536, |
| "grad_norm": 18.75, |
| "learning_rate": 1.5118518518518519e-05, |
| "loss": 19.2895, |
| "mean_token_accuracy": 0.6946466054767371, |
| "num_tokens": 18755079.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 1.1710849691182375, |
| "epoch": 1.552, |
| "grad_norm": 19.375, |
| "learning_rate": 1.5044444444444445e-05, |
| "loss": 18.9073, |
| "mean_token_accuracy": 0.699705482646823, |
| "num_tokens": 18956248.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 1.163971472159028, |
| "epoch": 1.568, |
| "grad_norm": 18.5, |
| "learning_rate": 1.497037037037037e-05, |
| "loss": 18.7379, |
| "mean_token_accuracy": 0.7023108277469874, |
| "num_tokens": 19150315.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 1.1755164857953786, |
| "epoch": 1.584, |
| "grad_norm": 17.75, |
| "learning_rate": 1.4896296296296298e-05, |
| "loss": 18.8826, |
| "mean_token_accuracy": 0.6997408363968134, |
| "num_tokens": 19344260.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 1.2020615819841622, |
| "epoch": 1.6, |
| "grad_norm": 17.125, |
| "learning_rate": 1.4822222222222225e-05, |
| "loss": 19.3858, |
| "mean_token_accuracy": 0.6933612376451492, |
| "num_tokens": 19532552.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_biology_entropy": 1.1451181559562682, |
| "eval_biology_loss": 1.1767185926437378, |
| "eval_biology_mean_token_accuracy": 0.7013368840217591, |
| "eval_biology_num_tokens": 19532552.0, |
| "eval_biology_runtime": 48.6261, |
| "eval_biology_samples_per_second": 10.283, |
| "eval_biology_steps_per_second": 2.571, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_chemistry_entropy": 0.8642943887710571, |
| "eval_chemistry_loss": 0.8798553347587585, |
| "eval_chemistry_mean_token_accuracy": 0.7664505195617676, |
| "eval_chemistry_num_tokens": 19532552.0, |
| "eval_chemistry_runtime": 59.8839, |
| "eval_chemistry_samples_per_second": 8.349, |
| "eval_chemistry_steps_per_second": 2.087, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_math_entropy": 0.7490488801002503, |
| "eval_math_loss": 0.9804874062538147, |
| "eval_math_mean_token_accuracy": 0.7602896738052368, |
| "eval_math_num_tokens": 19532552.0, |
| "eval_math_runtime": 61.7317, |
| "eval_math_samples_per_second": 8.1, |
| "eval_math_steps_per_second": 2.025, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_physics_entropy": 0.8397411880493164, |
| "eval_physics_loss": 0.885618269443512, |
| "eval_physics_mean_token_accuracy": 0.7722613711357117, |
| "eval_physics_num_tokens": 19532552.0, |
| "eval_physics_runtime": 70.4574, |
| "eval_physics_samples_per_second": 7.096, |
| "eval_physics_steps_per_second": 1.774, |
| "step": 1000 |
| }, |
| { |
| "entropy": 1.1645312760025264, |
| "epoch": 1.616, |
| "grad_norm": 17.125, |
| "learning_rate": 1.474814814814815e-05, |
| "loss": 18.8318, |
| "mean_token_accuracy": 0.7000049009919167, |
| "num_tokens": 19732719.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 1.2018159918487072, |
| "epoch": 1.6320000000000001, |
| "grad_norm": 19.625, |
| "learning_rate": 1.4674074074074076e-05, |
| "loss": 19.3741, |
| "mean_token_accuracy": 0.6942509710788727, |
| "num_tokens": 19926830.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 1.1848741736263038, |
| "epoch": 1.6480000000000001, |
| "grad_norm": 16.25, |
| "learning_rate": 1.46e-05, |
| "loss": 19.0931, |
| "mean_token_accuracy": 0.6962833561003208, |
| "num_tokens": 20118800.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 1.1461675189435483, |
| "epoch": 1.6640000000000001, |
| "grad_norm": 16.5, |
| "learning_rate": 1.4525925925925927e-05, |
| "loss": 18.5384, |
| "mean_token_accuracy": 0.7037994157522917, |
| "num_tokens": 20320511.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 1.1853893544524907, |
| "epoch": 1.6800000000000002, |
| "grad_norm": 18.375, |
| "learning_rate": 1.4451851851851852e-05, |
| "loss": 18.9769, |
| "mean_token_accuracy": 0.6986714884638786, |
| "num_tokens": 20513393.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 1.1721675164997578, |
| "epoch": 1.696, |
| "grad_norm": 17.5, |
| "learning_rate": 1.4377777777777779e-05, |
| "loss": 18.9508, |
| "mean_token_accuracy": 0.7003318756818772, |
| "num_tokens": 20707237.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 1.1738170266151429, |
| "epoch": 1.712, |
| "grad_norm": 19.5, |
| "learning_rate": 1.4303703703703703e-05, |
| "loss": 18.9752, |
| "mean_token_accuracy": 0.6993441980332136, |
| "num_tokens": 20910419.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 1.190333865955472, |
| "epoch": 1.728, |
| "grad_norm": 18.5, |
| "learning_rate": 1.4229629629629632e-05, |
| "loss": 19.1838, |
| "mean_token_accuracy": 0.6956166718155146, |
| "num_tokens": 21107498.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 1.1574083410203457, |
| "epoch": 1.744, |
| "grad_norm": 18.25, |
| "learning_rate": 1.4155555555555556e-05, |
| "loss": 18.5378, |
| "mean_token_accuracy": 0.7021385233849287, |
| "num_tokens": 21303955.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 1.1666433937847613, |
| "epoch": 1.76, |
| "grad_norm": 18.75, |
| "learning_rate": 1.4081481481481483e-05, |
| "loss": 18.9266, |
| "mean_token_accuracy": 0.7011374026536942, |
| "num_tokens": 21499572.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_biology_entropy": 1.1345319437980652, |
| "eval_biology_loss": 1.1725776195526123, |
| "eval_biology_mean_token_accuracy": 0.7024298944473266, |
| "eval_biology_num_tokens": 21499572.0, |
| "eval_biology_runtime": 48.5727, |
| "eval_biology_samples_per_second": 10.294, |
| "eval_biology_steps_per_second": 2.573, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_chemistry_entropy": 0.8619537029266358, |
| "eval_chemistry_loss": 0.8766760230064392, |
| "eval_chemistry_mean_token_accuracy": 0.7667445015907287, |
| "eval_chemistry_num_tokens": 21499572.0, |
| "eval_chemistry_runtime": 60.4564, |
| "eval_chemistry_samples_per_second": 8.27, |
| "eval_chemistry_steps_per_second": 2.068, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_math_entropy": 0.7560438480377197, |
| "eval_math_loss": 0.9768902063369751, |
| "eval_math_mean_token_accuracy": 0.7610512175559998, |
| "eval_math_num_tokens": 21499572.0, |
| "eval_math_runtime": 61.7554, |
| "eval_math_samples_per_second": 8.096, |
| "eval_math_steps_per_second": 2.024, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_physics_entropy": 0.840686586856842, |
| "eval_physics_loss": 0.8825888633728027, |
| "eval_physics_mean_token_accuracy": 0.7726316556930543, |
| "eval_physics_num_tokens": 21499572.0, |
| "eval_physics_runtime": 70.3673, |
| "eval_physics_samples_per_second": 7.106, |
| "eval_physics_steps_per_second": 1.776, |
| "step": 1100 |
| }, |
| { |
| "entropy": 1.177320409566164, |
| "epoch": 1.776, |
| "grad_norm": 17.875, |
| "learning_rate": 1.400740740740741e-05, |
| "loss": 18.9676, |
| "mean_token_accuracy": 0.6986722864210606, |
| "num_tokens": 21692804.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 1.148191200569272, |
| "epoch": 1.792, |
| "grad_norm": 19.875, |
| "learning_rate": 1.3933333333333334e-05, |
| "loss": 18.5112, |
| "mean_token_accuracy": 0.7040422059595585, |
| "num_tokens": 21894218.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 1.1709640648216009, |
| "epoch": 1.808, |
| "grad_norm": 19.5, |
| "learning_rate": 1.385925925925926e-05, |
| "loss": 18.8424, |
| "mean_token_accuracy": 0.7009096905589104, |
| "num_tokens": 22082522.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 1.1934551119804382, |
| "epoch": 1.8239999999999998, |
| "grad_norm": 19.375, |
| "learning_rate": 1.3785185185185186e-05, |
| "loss": 19.3396, |
| "mean_token_accuracy": 0.693663826212287, |
| "num_tokens": 22278933.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 1.2042058877646924, |
| "epoch": 1.8399999999999999, |
| "grad_norm": 19.375, |
| "learning_rate": 1.3711111111111112e-05, |
| "loss": 19.393, |
| "mean_token_accuracy": 0.6937405589967967, |
| "num_tokens": 22473801.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 1.1648973379284144, |
| "epoch": 1.8559999999999999, |
| "grad_norm": 18.125, |
| "learning_rate": 1.3637037037037037e-05, |
| "loss": 18.7484, |
| "mean_token_accuracy": 0.6991217479109764, |
| "num_tokens": 22677853.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 1.1554684847593308, |
| "epoch": 1.8719999999999999, |
| "grad_norm": 17.375, |
| "learning_rate": 1.3562962962962965e-05, |
| "loss": 18.5305, |
| "mean_token_accuracy": 0.7038368381559849, |
| "num_tokens": 22874965.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 1.1899018451571464, |
| "epoch": 1.888, |
| "grad_norm": 20.75, |
| "learning_rate": 1.3488888888888888e-05, |
| "loss": 19.2428, |
| "mean_token_accuracy": 0.6950660139322281, |
| "num_tokens": 23068892.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 1.1851763129234314, |
| "epoch": 1.904, |
| "grad_norm": 18.375, |
| "learning_rate": 1.3414814814814817e-05, |
| "loss": 19.126, |
| "mean_token_accuracy": 0.6976218212395906, |
| "num_tokens": 23263827.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 1.1869227845221757, |
| "epoch": 1.92, |
| "grad_norm": 18.375, |
| "learning_rate": 1.3340740740740741e-05, |
| "loss": 19.135, |
| "mean_token_accuracy": 0.6959322843700647, |
| "num_tokens": 23463627.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_biology_entropy": 1.1337207446098327, |
| "eval_biology_loss": 1.168716311454773, |
| "eval_biology_mean_token_accuracy": 0.7030426645278931, |
| "eval_biology_num_tokens": 23463627.0, |
| "eval_biology_runtime": 48.5387, |
| "eval_biology_samples_per_second": 10.301, |
| "eval_biology_steps_per_second": 2.575, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_chemistry_entropy": 0.8601148505210876, |
| "eval_chemistry_loss": 0.8744351267814636, |
| "eval_chemistry_mean_token_accuracy": 0.767286482334137, |
| "eval_chemistry_num_tokens": 23463627.0, |
| "eval_chemistry_runtime": 60.2148, |
| "eval_chemistry_samples_per_second": 8.304, |
| "eval_chemistry_steps_per_second": 2.076, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_math_entropy": 0.7519172282218933, |
| "eval_math_loss": 0.9753768444061279, |
| "eval_math_mean_token_accuracy": 0.7615019774436951, |
| "eval_math_num_tokens": 23463627.0, |
| "eval_math_runtime": 61.7169, |
| "eval_math_samples_per_second": 8.102, |
| "eval_math_steps_per_second": 2.025, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_physics_entropy": 0.836491331577301, |
| "eval_physics_loss": 0.8801184296607971, |
| "eval_physics_mean_token_accuracy": 0.7731836423873901, |
| "eval_physics_num_tokens": 23463627.0, |
| "eval_physics_runtime": 70.3444, |
| "eval_physics_samples_per_second": 7.108, |
| "eval_physics_steps_per_second": 1.777, |
| "step": 1200 |
| }, |
| { |
| "entropy": 1.1517000958323478, |
| "epoch": 1.936, |
| "grad_norm": 18.875, |
| "learning_rate": 1.3266666666666668e-05, |
| "loss": 18.5112, |
| "mean_token_accuracy": 0.7040315445512533, |
| "num_tokens": 23660418.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 1.172454860061407, |
| "epoch": 1.952, |
| "grad_norm": 18.75, |
| "learning_rate": 1.3192592592592594e-05, |
| "loss": 18.8708, |
| "mean_token_accuracy": 0.6998139064759016, |
| "num_tokens": 23858145.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 1.18152665682137, |
| "epoch": 1.968, |
| "grad_norm": 18.5, |
| "learning_rate": 1.311851851851852e-05, |
| "loss": 19.0753, |
| "mean_token_accuracy": 0.6981570664793253, |
| "num_tokens": 24053364.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 1.1768125779926777, |
| "epoch": 1.984, |
| "grad_norm": 17.625, |
| "learning_rate": 1.3044444444444446e-05, |
| "loss": 18.9463, |
| "mean_token_accuracy": 0.6988612022250891, |
| "num_tokens": 24249465.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 1.180902672186494, |
| "epoch": 2.0, |
| "grad_norm": 19.375, |
| "learning_rate": 1.297037037037037e-05, |
| "loss": 18.999, |
| "mean_token_accuracy": 0.7006669268012047, |
| "num_tokens": 24442582.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 1.1616276282817126, |
| "epoch": 2.016, |
| "grad_norm": 19.75, |
| "learning_rate": 1.2896296296296299e-05, |
| "loss": 18.592, |
| "mean_token_accuracy": 0.7041712146252394, |
| "num_tokens": 24632353.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 1.1689807120710611, |
| "epoch": 2.032, |
| "grad_norm": 18.625, |
| "learning_rate": 1.2822222222222222e-05, |
| "loss": 18.9039, |
| "mean_token_accuracy": 0.7014766734093427, |
| "num_tokens": 24822715.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 1.1456513587385415, |
| "epoch": 2.048, |
| "grad_norm": 20.0, |
| "learning_rate": 1.274814814814815e-05, |
| "loss": 18.4096, |
| "mean_token_accuracy": 0.7051771484315396, |
| "num_tokens": 25023118.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 1.1587952699512243, |
| "epoch": 2.064, |
| "grad_norm": 18.625, |
| "learning_rate": 1.2674074074074075e-05, |
| "loss": 18.6378, |
| "mean_token_accuracy": 0.7034870360046626, |
| "num_tokens": 25217414.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 1.1504007514566184, |
| "epoch": 2.08, |
| "grad_norm": 18.0, |
| "learning_rate": 1.2600000000000001e-05, |
| "loss": 18.4703, |
| "mean_token_accuracy": 0.7041630525141954, |
| "num_tokens": 25408961.0, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_biology_entropy": 1.1164145894050599, |
| "eval_biology_loss": 1.1683411598205566, |
| "eval_biology_mean_token_accuracy": 0.7027085943222046, |
| "eval_biology_num_tokens": 25408961.0, |
| "eval_biology_runtime": 48.5837, |
| "eval_biology_samples_per_second": 10.292, |
| "eval_biology_steps_per_second": 2.573, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_chemistry_entropy": 0.8446620798110962, |
| "eval_chemistry_loss": 0.8756071925163269, |
| "eval_chemistry_mean_token_accuracy": 0.7672800846099853, |
| "eval_chemistry_num_tokens": 25408961.0, |
| "eval_chemistry_runtime": 60.224, |
| "eval_chemistry_samples_per_second": 8.302, |
| "eval_chemistry_steps_per_second": 2.076, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_math_entropy": 0.7416602709293365, |
| "eval_math_loss": 0.9767736792564392, |
| "eval_math_mean_token_accuracy": 0.7612695918083191, |
| "eval_math_num_tokens": 25408961.0, |
| "eval_math_runtime": 61.7354, |
| "eval_math_samples_per_second": 8.099, |
| "eval_math_steps_per_second": 2.025, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_physics_entropy": 0.822511604309082, |
| "eval_physics_loss": 0.8807807564735413, |
| "eval_physics_mean_token_accuracy": 0.7734324297904969, |
| "eval_physics_num_tokens": 25408961.0, |
| "eval_physics_runtime": 70.3722, |
| "eval_physics_samples_per_second": 7.105, |
| "eval_physics_steps_per_second": 1.776, |
| "step": 1300 |
| }, |
| { |
| "entropy": 1.145626274123788, |
| "epoch": 2.096, |
| "grad_norm": 20.75, |
| "learning_rate": 1.2525925925925928e-05, |
| "loss": 18.4669, |
| "mean_token_accuracy": 0.7053351275622844, |
| "num_tokens": 25600511.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 1.1261590894311666, |
| "epoch": 2.112, |
| "grad_norm": 19.375, |
| "learning_rate": 1.2451851851851853e-05, |
| "loss": 18.0421, |
| "mean_token_accuracy": 0.7101508729159832, |
| "num_tokens": 25796565.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 1.1319866240024568, |
| "epoch": 2.128, |
| "grad_norm": 18.375, |
| "learning_rate": 1.237777777777778e-05, |
| "loss": 18.2326, |
| "mean_token_accuracy": 0.7063661482185125, |
| "num_tokens": 25991156.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 1.12694109082222, |
| "epoch": 2.144, |
| "grad_norm": 21.625, |
| "learning_rate": 1.2303703703703704e-05, |
| "loss": 18.27, |
| "mean_token_accuracy": 0.7078616585582495, |
| "num_tokens": 26193237.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 1.1670064296573401, |
| "epoch": 2.16, |
| "grad_norm": 20.0, |
| "learning_rate": 1.222962962962963e-05, |
| "loss": 18.6321, |
| "mean_token_accuracy": 0.704596522077918, |
| "num_tokens": 26387993.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 1.1611683428287507, |
| "epoch": 2.176, |
| "grad_norm": 19.75, |
| "learning_rate": 1.2155555555555555e-05, |
| "loss": 18.8084, |
| "mean_token_accuracy": 0.7007863517850638, |
| "num_tokens": 26585269.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 1.1334992978721856, |
| "epoch": 2.192, |
| "grad_norm": 17.0, |
| "learning_rate": 1.2081481481481484e-05, |
| "loss": 18.1002, |
| "mean_token_accuracy": 0.7102227192372084, |
| "num_tokens": 26776318.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 1.142113695293665, |
| "epoch": 2.208, |
| "grad_norm": 18.25, |
| "learning_rate": 1.2007407407407408e-05, |
| "loss": 18.4288, |
| "mean_token_accuracy": 0.7056139782071114, |
| "num_tokens": 26974420.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 1.165258849412203, |
| "epoch": 2.224, |
| "grad_norm": 18.375, |
| "learning_rate": 1.1933333333333335e-05, |
| "loss": 18.8072, |
| "mean_token_accuracy": 0.7021366007626056, |
| "num_tokens": 27167577.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 1.1230817057192326, |
| "epoch": 2.24, |
| "grad_norm": 18.0, |
| "learning_rate": 1.185925925925926e-05, |
| "loss": 18.0154, |
| "mean_token_accuracy": 0.7094326011836529, |
| "num_tokens": 27364189.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_biology_entropy": 1.107084683418274, |
| "eval_biology_loss": 1.166341781616211, |
| "eval_biology_mean_token_accuracy": 0.7033038935661315, |
| "eval_biology_num_tokens": 27364189.0, |
| "eval_biology_runtime": 48.5794, |
| "eval_biology_samples_per_second": 10.292, |
| "eval_biology_steps_per_second": 2.573, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_chemistry_entropy": 0.8436218018531799, |
| "eval_chemistry_loss": 0.8749056458473206, |
| "eval_chemistry_mean_token_accuracy": 0.7673236474990844, |
| "eval_chemistry_num_tokens": 27364189.0, |
| "eval_chemistry_runtime": 60.2275, |
| "eval_chemistry_samples_per_second": 8.302, |
| "eval_chemistry_steps_per_second": 2.075, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_math_entropy": 0.7436552357673645, |
| "eval_math_loss": 0.9768530130386353, |
| "eval_math_mean_token_accuracy": 0.7615942449569703, |
| "eval_math_num_tokens": 27364189.0, |
| "eval_math_runtime": 61.7353, |
| "eval_math_samples_per_second": 8.099, |
| "eval_math_steps_per_second": 2.025, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_physics_entropy": 0.8238044924736023, |
| "eval_physics_loss": 0.880571186542511, |
| "eval_physics_mean_token_accuracy": 0.7732309465408325, |
| "eval_physics_num_tokens": 27364189.0, |
| "eval_physics_runtime": 70.3425, |
| "eval_physics_samples_per_second": 7.108, |
| "eval_physics_steps_per_second": 1.777, |
| "step": 1400 |
| }, |
| { |
| "entropy": 1.1227998584508896, |
| "epoch": 2.2560000000000002, |
| "grad_norm": 17.875, |
| "learning_rate": 1.1785185185185186e-05, |
| "loss": 17.9995, |
| "mean_token_accuracy": 0.71092384532094, |
| "num_tokens": 27557387.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 1.1192971892654895, |
| "epoch": 2.2720000000000002, |
| "grad_norm": 19.5, |
| "learning_rate": 1.1711111111111113e-05, |
| "loss": 18.0703, |
| "mean_token_accuracy": 0.7088606022298336, |
| "num_tokens": 27755725.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 1.157552171498537, |
| "epoch": 2.288, |
| "grad_norm": 18.75, |
| "learning_rate": 1.1637037037037037e-05, |
| "loss": 18.6818, |
| "mean_token_accuracy": 0.7010403741151094, |
| "num_tokens": 27950694.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 1.1524705573916436, |
| "epoch": 2.304, |
| "grad_norm": 17.75, |
| "learning_rate": 1.1562962962962964e-05, |
| "loss": 18.6601, |
| "mean_token_accuracy": 0.7030924465507269, |
| "num_tokens": 28150719.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 1.1215086288750171, |
| "epoch": 2.32, |
| "grad_norm": 17.5, |
| "learning_rate": 1.1488888888888889e-05, |
| "loss": 17.9268, |
| "mean_token_accuracy": 0.7104179698973894, |
| "num_tokens": 28348652.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 1.1350885152816772, |
| "epoch": 2.336, |
| "grad_norm": 18.375, |
| "learning_rate": 1.1414814814814817e-05, |
| "loss": 18.3565, |
| "mean_token_accuracy": 0.7067790202796459, |
| "num_tokens": 28542945.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 1.156265541538596, |
| "epoch": 2.352, |
| "grad_norm": 19.0, |
| "learning_rate": 1.1340740740740742e-05, |
| "loss": 18.6992, |
| "mean_token_accuracy": 0.7013768840581178, |
| "num_tokens": 28731927.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 1.1396565582603215, |
| "epoch": 2.368, |
| "grad_norm": 18.75, |
| "learning_rate": 1.1266666666666668e-05, |
| "loss": 18.2949, |
| "mean_token_accuracy": 0.7059750188142061, |
| "num_tokens": 28929298.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 1.1448044694960118, |
| "epoch": 2.384, |
| "grad_norm": 20.625, |
| "learning_rate": 1.1192592592592593e-05, |
| "loss": 18.526, |
| "mean_token_accuracy": 0.703592960909009, |
| "num_tokens": 29121142.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 1.140185246989131, |
| "epoch": 2.4, |
| "grad_norm": 18.0, |
| "learning_rate": 1.111851851851852e-05, |
| "loss": 18.3273, |
| "mean_token_accuracy": 0.706566022336483, |
| "num_tokens": 29317919.0, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_biology_entropy": 1.1156310276985169, |
| "eval_biology_loss": 1.1647558212280273, |
| "eval_biology_mean_token_accuracy": 0.7032402672767639, |
| "eval_biology_num_tokens": 29317919.0, |
| "eval_biology_runtime": 48.611, |
| "eval_biology_samples_per_second": 10.286, |
| "eval_biology_steps_per_second": 2.571, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_chemistry_entropy": 0.8463425951004029, |
| "eval_chemistry_loss": 0.8742334246635437, |
| "eval_chemistry_mean_token_accuracy": 0.767361388683319, |
| "eval_chemistry_num_tokens": 29317919.0, |
| "eval_chemistry_runtime": 59.9689, |
| "eval_chemistry_samples_per_second": 8.338, |
| "eval_chemistry_steps_per_second": 2.084, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_math_entropy": 0.7472673971652984, |
| "eval_math_loss": 0.9761422872543335, |
| "eval_math_mean_token_accuracy": 0.7615765709877014, |
| "eval_math_num_tokens": 29317919.0, |
| "eval_math_runtime": 61.7442, |
| "eval_math_samples_per_second": 8.098, |
| "eval_math_steps_per_second": 2.024, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_physics_entropy": 0.8270321841239929, |
| "eval_physics_loss": 0.8801943063735962, |
| "eval_physics_mean_token_accuracy": 0.7734404511451721, |
| "eval_physics_num_tokens": 29317919.0, |
| "eval_physics_runtime": 70.5165, |
| "eval_physics_samples_per_second": 7.091, |
| "eval_physics_steps_per_second": 1.773, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 3000, |
| "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": 3.305483613425587e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
