| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8, |
| "eval_steps": 100, |
| "global_step": 500, |
| "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 |
| } |
| ], |
| "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": 1.0976936565348991e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
