| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8, |
| "eval_steps": 100, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.6734127338975668, |
| "epoch": 0.004, |
| "grad_norm": 1000.0, |
| "learning_rate": 1.8e-07, |
| "loss": 28.5463, |
| "mean_token_accuracy": 0.7051723279058933, |
| "num_tokens": 89176.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.7554282372817397, |
| "epoch": 0.008, |
| "grad_norm": 848.0, |
| "learning_rate": 3.8e-07, |
| "loss": 30.5507, |
| "mean_token_accuracy": 0.6821797413751483, |
| "num_tokens": 173886.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.7452052749693394, |
| "epoch": 0.012, |
| "grad_norm": 700.0, |
| "learning_rate": 5.800000000000001e-07, |
| "loss": 28.0843, |
| "mean_token_accuracy": 0.6968917248770594, |
| "num_tokens": 258970.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.8406938400119544, |
| "epoch": 0.016, |
| "grad_norm": 588.0, |
| "learning_rate": 7.8e-07, |
| "loss": 28.3624, |
| "mean_token_accuracy": 0.6884651094675064, |
| "num_tokens": 338352.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.8782084910199046, |
| "epoch": 0.02, |
| "grad_norm": 556.0, |
| "learning_rate": 9.800000000000001e-07, |
| "loss": 25.7081, |
| "mean_token_accuracy": 0.7061796801164746, |
| "num_tokens": 424243.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.9611807337030769, |
| "epoch": 0.024, |
| "grad_norm": 456.0, |
| "learning_rate": 1.1800000000000001e-06, |
| "loss": 25.387, |
| "mean_token_accuracy": 0.6989632658660412, |
| "num_tokens": 505613.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.9614389628171921, |
| "epoch": 0.028, |
| "grad_norm": 290.0, |
| "learning_rate": 1.3800000000000001e-06, |
| "loss": 22.9903, |
| "mean_token_accuracy": 0.7096886133775115, |
| "num_tokens": 584157.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.9275373946875334, |
| "epoch": 0.032, |
| "grad_norm": 161.0, |
| "learning_rate": 1.5800000000000001e-06, |
| "loss": 20.0946, |
| "mean_token_accuracy": 0.7300519198179245, |
| "num_tokens": 671193.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.0108212113380433, |
| "epoch": 0.036, |
| "grad_norm": 217.0, |
| "learning_rate": 1.7800000000000001e-06, |
| "loss": 20.6725, |
| "mean_token_accuracy": 0.7165856244042516, |
| "num_tokens": 753947.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.9366745728999376, |
| "epoch": 0.04, |
| "grad_norm": 162.0, |
| "learning_rate": 1.98e-06, |
| "loss": 18.0538, |
| "mean_token_accuracy": 0.7409927822649479, |
| "num_tokens": 835868.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_biology_entropy": 1.5465301005840302, |
| "eval_biology_loss": 1.9649326801300049, |
| "eval_biology_mean_token_accuracy": 0.5973824737071991, |
| "eval_biology_num_tokens": 835868.0, |
| "eval_biology_runtime": 35.5773, |
| "eval_biology_samples_per_second": 14.054, |
| "eval_biology_steps_per_second": 14.054, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_chemistry_entropy": 1.0573365586400032, |
| "eval_chemistry_loss": 1.2894866466522217, |
| "eval_chemistry_mean_token_accuracy": 0.7121288641691208, |
| "eval_chemistry_num_tokens": 835868.0, |
| "eval_chemistry_runtime": 39.6571, |
| "eval_chemistry_samples_per_second": 12.608, |
| "eval_chemistry_steps_per_second": 12.608, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_math_entropy": 0.8270023443698883, |
| "eval_math_loss": 1.1661900281906128, |
| "eval_math_mean_token_accuracy": 0.737815534889698, |
| "eval_math_num_tokens": 835868.0, |
| "eval_math_runtime": 40.5371, |
| "eval_math_samples_per_second": 12.334, |
| "eval_math_steps_per_second": 12.334, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_physics_entropy": 0.9262812133431435, |
| "eval_physics_loss": 1.1149247884750366, |
| "eval_physics_mean_token_accuracy": 0.7413808185458183, |
| "eval_physics_num_tokens": 835868.0, |
| "eval_physics_runtime": 45.1205, |
| "eval_physics_samples_per_second": 11.081, |
| "eval_physics_steps_per_second": 11.081, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.8625543506816029, |
| "epoch": 0.044, |
| "grad_norm": 141.0, |
| "learning_rate": 2.1800000000000003e-06, |
| "loss": 16.1132, |
| "mean_token_accuracy": 0.7616209197789431, |
| "num_tokens": 917534.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.8609532468020916, |
| "epoch": 0.048, |
| "grad_norm": 142.0, |
| "learning_rate": 2.38e-06, |
| "loss": 15.8038, |
| "mean_token_accuracy": 0.7642258133739233, |
| "num_tokens": 1001008.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.8615515833720565, |
| "epoch": 0.052, |
| "grad_norm": 110.0, |
| "learning_rate": 2.5800000000000003e-06, |
| "loss": 15.6256, |
| "mean_token_accuracy": 0.7626194018870592, |
| "num_tokens": 1085098.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.9037158312276006, |
| "epoch": 0.056, |
| "grad_norm": 122.5, |
| "learning_rate": 2.7800000000000005e-06, |
| "loss": 16.4938, |
| "mean_token_accuracy": 0.7565715182572603, |
| "num_tokens": 1166615.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.8950596721842885, |
| "epoch": 0.06, |
| "grad_norm": 134.0, |
| "learning_rate": 2.9800000000000003e-06, |
| "loss": 14.5001, |
| "mean_token_accuracy": 0.7665418200194836, |
| "num_tokens": 1248387.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.961725745536387, |
| "epoch": 0.064, |
| "grad_norm": 100.0, |
| "learning_rate": 3.1800000000000005e-06, |
| "loss": 15.127, |
| "mean_token_accuracy": 0.7604502853006124, |
| "num_tokens": 1331208.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.881209403835237, |
| "epoch": 0.068, |
| "grad_norm": 98.5, |
| "learning_rate": 3.3800000000000007e-06, |
| "loss": 13.694, |
| "mean_token_accuracy": 0.7777196705341339, |
| "num_tokens": 1416841.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.8587444640696049, |
| "epoch": 0.072, |
| "grad_norm": 109.0, |
| "learning_rate": 3.58e-06, |
| "loss": 13.3488, |
| "mean_token_accuracy": 0.7776382105425, |
| "num_tokens": 1499449.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.8419531056657433, |
| "epoch": 0.076, |
| "grad_norm": 89.5, |
| "learning_rate": 3.7800000000000002e-06, |
| "loss": 13.184, |
| "mean_token_accuracy": 0.7732796184718609, |
| "num_tokens": 1585982.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.8316561704501509, |
| "epoch": 0.08, |
| "grad_norm": 83.0, |
| "learning_rate": 3.980000000000001e-06, |
| "loss": 13.2192, |
| "mean_token_accuracy": 0.7721541322767734, |
| "num_tokens": 1667532.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_biology_entropy": 1.3391264139413834, |
| "eval_biology_loss": 1.495794653892517, |
| "eval_biology_mean_token_accuracy": 0.6435496712327003, |
| "eval_biology_num_tokens": 1667532.0, |
| "eval_biology_runtime": 35.2419, |
| "eval_biology_samples_per_second": 14.188, |
| "eval_biology_steps_per_second": 14.188, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_chemistry_entropy": 0.9186333262324333, |
| "eval_chemistry_loss": 0.9441949725151062, |
| "eval_chemistry_mean_token_accuracy": 0.749591316819191, |
| "eval_chemistry_num_tokens": 1667532.0, |
| "eval_chemistry_runtime": 39.611, |
| "eval_chemistry_samples_per_second": 12.623, |
| "eval_chemistry_steps_per_second": 12.623, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_math_entropy": 0.7541183361709118, |
| "eval_math_loss": 0.8956651091575623, |
| "eval_math_mean_token_accuracy": 0.7658155815601349, |
| "eval_math_num_tokens": 1667532.0, |
| "eval_math_runtime": 40.4594, |
| "eval_math_samples_per_second": 12.358, |
| "eval_math_steps_per_second": 12.358, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_physics_entropy": 0.8000644188523293, |
| "eval_physics_loss": 0.8156371116638184, |
| "eval_physics_mean_token_accuracy": 0.7777305005192756, |
| "eval_physics_num_tokens": 1667532.0, |
| "eval_physics_runtime": 45.1972, |
| "eval_physics_samples_per_second": 11.063, |
| "eval_physics_steps_per_second": 11.063, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.7765617506578565, |
| "epoch": 0.084, |
| "grad_norm": 79.0, |
| "learning_rate": 4.18e-06, |
| "loss": 12.5271, |
| "mean_token_accuracy": 0.7859760526567697, |
| "num_tokens": 1750813.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.8027046866714954, |
| "epoch": 0.088, |
| "grad_norm": 82.0, |
| "learning_rate": 4.38e-06, |
| "loss": 12.8324, |
| "mean_token_accuracy": 0.7811258573085069, |
| "num_tokens": 1835489.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.8210387529805303, |
| "epoch": 0.092, |
| "grad_norm": 93.0, |
| "learning_rate": 4.58e-06, |
| "loss": 13.2166, |
| "mean_token_accuracy": 0.7749050311744213, |
| "num_tokens": 1915115.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.7716038260608912, |
| "epoch": 0.096, |
| "grad_norm": 106.5, |
| "learning_rate": 4.78e-06, |
| "loss": 12.3448, |
| "mean_token_accuracy": 0.7872315399348736, |
| "num_tokens": 2007176.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.7926006538793444, |
| "epoch": 0.1, |
| "grad_norm": 73.0, |
| "learning_rate": 4.980000000000001e-06, |
| "loss": 12.647, |
| "mean_token_accuracy": 0.7829932551831007, |
| "num_tokens": 2088696.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.8025551496073604, |
| "epoch": 0.104, |
| "grad_norm": 76.5, |
| "learning_rate": 5.18e-06, |
| "loss": 12.8826, |
| "mean_token_accuracy": 0.7798444323241711, |
| "num_tokens": 2171335.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.7691786218434572, |
| "epoch": 0.108, |
| "grad_norm": 90.5, |
| "learning_rate": 5.380000000000001e-06, |
| "loss": 12.3875, |
| "mean_token_accuracy": 0.7863950747996569, |
| "num_tokens": 2254168.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.7568587090820074, |
| "epoch": 0.112, |
| "grad_norm": 102.5, |
| "learning_rate": 5.580000000000001e-06, |
| "loss": 12.0152, |
| "mean_token_accuracy": 0.7904921755194664, |
| "num_tokens": 2342259.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.7691523030400276, |
| "epoch": 0.116, |
| "grad_norm": 81.0, |
| "learning_rate": 5.78e-06, |
| "loss": 12.3692, |
| "mean_token_accuracy": 0.7872932553291321, |
| "num_tokens": 2426289.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.8102743584662676, |
| "epoch": 0.12, |
| "grad_norm": 72.5, |
| "learning_rate": 5.98e-06, |
| "loss": 12.869, |
| "mean_token_accuracy": 0.7774799339473247, |
| "num_tokens": 2504279.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_biology_entropy": 1.2733513461351396, |
| "eval_biology_loss": 1.4364651441574097, |
| "eval_biology_mean_token_accuracy": 0.6550095283985138, |
| "eval_biology_num_tokens": 2504279.0, |
| "eval_biology_runtime": 35.2012, |
| "eval_biology_samples_per_second": 14.204, |
| "eval_biology_steps_per_second": 14.204, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_chemistry_entropy": 0.8685060097575188, |
| "eval_chemistry_loss": 0.891410768032074, |
| "eval_chemistry_mean_token_accuracy": 0.7606868423819542, |
| "eval_chemistry_num_tokens": 2504279.0, |
| "eval_chemistry_runtime": 39.6393, |
| "eval_chemistry_samples_per_second": 12.614, |
| "eval_chemistry_steps_per_second": 12.614, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_math_entropy": 0.7212547466754914, |
| "eval_math_loss": 0.8686274886131287, |
| "eval_math_mean_token_accuracy": 0.7728212839365005, |
| "eval_math_num_tokens": 2504279.0, |
| "eval_math_runtime": 40.496, |
| "eval_math_samples_per_second": 12.347, |
| "eval_math_steps_per_second": 12.347, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_physics_entropy": 0.7448382738828659, |
| "eval_physics_loss": 0.75321364402771, |
| "eval_physics_mean_token_accuracy": 0.7901370082497596, |
| "eval_physics_num_tokens": 2504279.0, |
| "eval_physics_runtime": 45.1204, |
| "eval_physics_samples_per_second": 11.081, |
| "eval_physics_steps_per_second": 11.081, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.785609095916152, |
| "epoch": 0.124, |
| "grad_norm": 72.5, |
| "learning_rate": 6.18e-06, |
| "loss": 12.587, |
| "mean_token_accuracy": 0.7802519340068101, |
| "num_tokens": 2583599.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.7176813660189509, |
| "epoch": 0.128, |
| "grad_norm": 68.0, |
| "learning_rate": 6.380000000000001e-06, |
| "loss": 11.598, |
| "mean_token_accuracy": 0.7966837007552385, |
| "num_tokens": 2663987.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.7790673697367311, |
| "epoch": 0.132, |
| "grad_norm": 80.0, |
| "learning_rate": 6.5800000000000005e-06, |
| "loss": 12.5265, |
| "mean_token_accuracy": 0.7850641790777445, |
| "num_tokens": 2743933.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.7665272958576679, |
| "epoch": 0.136, |
| "grad_norm": 58.0, |
| "learning_rate": 6.780000000000001e-06, |
| "loss": 12.1612, |
| "mean_token_accuracy": 0.792558753862977, |
| "num_tokens": 2829720.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.7513320775702595, |
| "epoch": 0.14, |
| "grad_norm": 63.5, |
| "learning_rate": 6.98e-06, |
| "loss": 12.1271, |
| "mean_token_accuracy": 0.7889207687228919, |
| "num_tokens": 2915814.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.7429860392585397, |
| "epoch": 0.144, |
| "grad_norm": 93.0, |
| "learning_rate": 7.180000000000001e-06, |
| "loss": 11.8571, |
| "mean_token_accuracy": 0.7946608085185289, |
| "num_tokens": 2997824.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.7470190897583961, |
| "epoch": 0.148, |
| "grad_norm": 78.0, |
| "learning_rate": 7.3800000000000005e-06, |
| "loss": 12.0544, |
| "mean_token_accuracy": 0.7908409368246794, |
| "num_tokens": 3076422.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.705881585367024, |
| "epoch": 0.152, |
| "grad_norm": 67.0, |
| "learning_rate": 7.58e-06, |
| "loss": 11.3247, |
| "mean_token_accuracy": 0.799928180873394, |
| "num_tokens": 3159946.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.7021555813029409, |
| "epoch": 0.156, |
| "grad_norm": 71.0, |
| "learning_rate": 7.78e-06, |
| "loss": 11.1229, |
| "mean_token_accuracy": 0.8013802103698253, |
| "num_tokens": 3247218.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.7140809871256352, |
| "epoch": 0.16, |
| "grad_norm": 70.5, |
| "learning_rate": 7.980000000000002e-06, |
| "loss": 11.5837, |
| "mean_token_accuracy": 0.7982432089745999, |
| "num_tokens": 3330597.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_biology_entropy": 1.2522204325199127, |
| "eval_biology_loss": 1.4104059934616089, |
| "eval_biology_mean_token_accuracy": 0.6601863117814064, |
| "eval_biology_num_tokens": 3330597.0, |
| "eval_biology_runtime": 35.3004, |
| "eval_biology_samples_per_second": 14.164, |
| "eval_biology_steps_per_second": 14.164, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_chemistry_entropy": 0.8451869760751725, |
| "eval_chemistry_loss": 0.8661983609199524, |
| "eval_chemistry_mean_token_accuracy": 0.7661204301714897, |
| "eval_chemistry_num_tokens": 3330597.0, |
| "eval_chemistry_runtime": 39.7099, |
| "eval_chemistry_samples_per_second": 12.591, |
| "eval_chemistry_steps_per_second": 12.591, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_math_entropy": 0.7037465732693672, |
| "eval_math_loss": 0.8592318296432495, |
| "eval_math_mean_token_accuracy": 0.7752037541866302, |
| "eval_math_num_tokens": 3330597.0, |
| "eval_math_runtime": 40.5913, |
| "eval_math_samples_per_second": 12.318, |
| "eval_math_steps_per_second": 12.318, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_physics_entropy": 0.7166930376887322, |
| "eval_physics_loss": 0.7220315933227539, |
| "eval_physics_mean_token_accuracy": 0.797553953409195, |
| "eval_physics_num_tokens": 3330597.0, |
| "eval_physics_runtime": 45.1326, |
| "eval_physics_samples_per_second": 11.078, |
| "eval_physics_steps_per_second": 11.078, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.7665172951295972, |
| "epoch": 0.164, |
| "grad_norm": 76.0, |
| "learning_rate": 8.18e-06, |
| "loss": 12.0954, |
| "mean_token_accuracy": 0.7892688918858767, |
| "num_tokens": 3414445.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.7116625974886119, |
| "epoch": 0.168, |
| "grad_norm": 82.0, |
| "learning_rate": 8.380000000000001e-06, |
| "loss": 11.522, |
| "mean_token_accuracy": 0.7954209111630917, |
| "num_tokens": 3496104.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.7325116093270481, |
| "epoch": 0.172, |
| "grad_norm": 63.75, |
| "learning_rate": 8.580000000000001e-06, |
| "loss": 11.8769, |
| "mean_token_accuracy": 0.7929634388536215, |
| "num_tokens": 3576979.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.713999939430505, |
| "epoch": 0.176, |
| "grad_norm": 87.5, |
| "learning_rate": 8.78e-06, |
| "loss": 11.4054, |
| "mean_token_accuracy": 0.7975817665457725, |
| "num_tokens": 3658264.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.7327057829126715, |
| "epoch": 0.18, |
| "grad_norm": 80.5, |
| "learning_rate": 8.98e-06, |
| "loss": 11.7006, |
| "mean_token_accuracy": 0.7944537442177534, |
| "num_tokens": 3739142.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.7196770435199141, |
| "epoch": 0.184, |
| "grad_norm": 72.5, |
| "learning_rate": 9.180000000000002e-06, |
| "loss": 11.5975, |
| "mean_token_accuracy": 0.7943054404109716, |
| "num_tokens": 3821352.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.6925434624776244, |
| "epoch": 0.188, |
| "grad_norm": 65.0, |
| "learning_rate": 9.38e-06, |
| "loss": 11.1089, |
| "mean_token_accuracy": 0.8022922430187464, |
| "num_tokens": 3905291.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.6977481247857213, |
| "epoch": 0.192, |
| "grad_norm": 59.5, |
| "learning_rate": 9.58e-06, |
| "loss": 11.1687, |
| "mean_token_accuracy": 0.803613081201911, |
| "num_tokens": 3995568.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.7005923493765295, |
| "epoch": 0.196, |
| "grad_norm": 73.5, |
| "learning_rate": 9.780000000000001e-06, |
| "loss": 11.3477, |
| "mean_token_accuracy": 0.8010011687874794, |
| "num_tokens": 4075670.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.6876647426746786, |
| "epoch": 0.2, |
| "grad_norm": 70.0, |
| "learning_rate": 9.980000000000001e-06, |
| "loss": 10.9642, |
| "mean_token_accuracy": 0.8049134809523821, |
| "num_tokens": 4160918.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_biology_entropy": 1.2019921021461486, |
| "eval_biology_loss": 1.389614462852478, |
| "eval_biology_mean_token_accuracy": 0.6654457822442055, |
| "eval_biology_num_tokens": 4160918.0, |
| "eval_biology_runtime": 35.0884, |
| "eval_biology_samples_per_second": 14.25, |
| "eval_biology_steps_per_second": 14.25, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_chemistry_entropy": 0.8132011856138707, |
| "eval_chemistry_loss": 0.8497000932693481, |
| "eval_chemistry_mean_token_accuracy": 0.7708191834092141, |
| "eval_chemistry_num_tokens": 4160918.0, |
| "eval_chemistry_runtime": 39.8091, |
| "eval_chemistry_samples_per_second": 12.56, |
| "eval_chemistry_steps_per_second": 12.56, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_math_entropy": 0.6891986537277699, |
| "eval_math_loss": 0.8553754687309265, |
| "eval_math_mean_token_accuracy": 0.7759535777568817, |
| "eval_math_num_tokens": 4160918.0, |
| "eval_math_runtime": 40.7076, |
| "eval_math_samples_per_second": 12.283, |
| "eval_math_steps_per_second": 12.283, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_physics_entropy": 0.6950600004792213, |
| "eval_physics_loss": 0.7005596160888672, |
| "eval_physics_mean_token_accuracy": 0.8021351820230485, |
| "eval_physics_num_tokens": 4160918.0, |
| "eval_physics_runtime": 45.2305, |
| "eval_physics_samples_per_second": 11.054, |
| "eval_physics_steps_per_second": 11.054, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.6887986609712243, |
| "epoch": 0.204, |
| "grad_norm": 61.75, |
| "learning_rate": 1.018e-05, |
| "loss": 11.1871, |
| "mean_token_accuracy": 0.8051418982446193, |
| "num_tokens": 4238810.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.6818487482145429, |
| "epoch": 0.208, |
| "grad_norm": 64.0, |
| "learning_rate": 1.038e-05, |
| "loss": 10.9951, |
| "mean_token_accuracy": 0.8058457836508751, |
| "num_tokens": 4321436.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.7008362987078727, |
| "epoch": 0.212, |
| "grad_norm": 67.5, |
| "learning_rate": 1.0580000000000002e-05, |
| "loss": 11.0955, |
| "mean_token_accuracy": 0.8010448336601257, |
| "num_tokens": 4401710.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.7055313820019364, |
| "epoch": 0.216, |
| "grad_norm": 62.25, |
| "learning_rate": 1.0780000000000002e-05, |
| "loss": 11.4932, |
| "mean_token_accuracy": 0.79723966345191, |
| "num_tokens": 4482225.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.6803635071963072, |
| "epoch": 0.22, |
| "grad_norm": 68.5, |
| "learning_rate": 1.0980000000000002e-05, |
| "loss": 11.0034, |
| "mean_token_accuracy": 0.804273284226656, |
| "num_tokens": 4564662.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.667565680295229, |
| "epoch": 0.224, |
| "grad_norm": 52.0, |
| "learning_rate": 1.1180000000000001e-05, |
| "loss": 10.6657, |
| "mean_token_accuracy": 0.8107417456805706, |
| "num_tokens": 4648491.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.6490520000457763, |
| "epoch": 0.228, |
| "grad_norm": 56.5, |
| "learning_rate": 1.138e-05, |
| "loss": 10.5546, |
| "mean_token_accuracy": 0.8112937267869711, |
| "num_tokens": 4731596.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.7194359874352813, |
| "epoch": 0.232, |
| "grad_norm": 58.25, |
| "learning_rate": 1.1580000000000001e-05, |
| "loss": 11.4255, |
| "mean_token_accuracy": 0.7990602564066649, |
| "num_tokens": 4813449.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.6862584982067347, |
| "epoch": 0.236, |
| "grad_norm": 50.25, |
| "learning_rate": 1.178e-05, |
| "loss": 11.0007, |
| "mean_token_accuracy": 0.8042842660099268, |
| "num_tokens": 4899144.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.6895454197190702, |
| "epoch": 0.24, |
| "grad_norm": 58.5, |
| "learning_rate": 1.198e-05, |
| "loss": 11.1171, |
| "mean_token_accuracy": 0.8028610210865736, |
| "num_tokens": 4986175.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_biology_entropy": 1.2410894528031349, |
| "eval_biology_loss": 1.3766074180603027, |
| "eval_biology_mean_token_accuracy": 0.6672532483935356, |
| "eval_biology_num_tokens": 4986175.0, |
| "eval_biology_runtime": 35.1026, |
| "eval_biology_samples_per_second": 14.244, |
| "eval_biology_steps_per_second": 14.244, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_chemistry_entropy": 0.8104133826196194, |
| "eval_chemistry_loss": 0.8397422432899475, |
| "eval_chemistry_mean_token_accuracy": 0.7722517918944359, |
| "eval_chemistry_num_tokens": 4986175.0, |
| "eval_chemistry_runtime": 39.6397, |
| "eval_chemistry_samples_per_second": 12.614, |
| "eval_chemistry_steps_per_second": 12.614, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_math_entropy": 0.6969810444712639, |
| "eval_math_loss": 0.8505039215087891, |
| "eval_math_mean_token_accuracy": 0.7772268445491791, |
| "eval_math_num_tokens": 4986175.0, |
| "eval_math_runtime": 40.4861, |
| "eval_math_samples_per_second": 12.35, |
| "eval_math_steps_per_second": 12.35, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_physics_entropy": 0.6853992799520493, |
| "eval_physics_loss": 0.6912311911582947, |
| "eval_physics_mean_token_accuracy": 0.8048652278184891, |
| "eval_physics_num_tokens": 4986175.0, |
| "eval_physics_runtime": 45.4233, |
| "eval_physics_samples_per_second": 11.008, |
| "eval_physics_steps_per_second": 11.008, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.6969290849752724, |
| "epoch": 0.244, |
| "grad_norm": 65.0, |
| "learning_rate": 1.218e-05, |
| "loss": 11.151, |
| "mean_token_accuracy": 0.8016246553510428, |
| "num_tokens": 5071994.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.6583109201863409, |
| "epoch": 0.248, |
| "grad_norm": 57.5, |
| "learning_rate": 1.2380000000000002e-05, |
| "loss": 10.5979, |
| "mean_token_accuracy": 0.8095750134438277, |
| "num_tokens": 5164741.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.7111584974452854, |
| "epoch": 0.252, |
| "grad_norm": 81.5, |
| "learning_rate": 1.2580000000000002e-05, |
| "loss": 11.3705, |
| "mean_token_accuracy": 0.7996403712779283, |
| "num_tokens": 5245878.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.6798671390861273, |
| "epoch": 0.256, |
| "grad_norm": 65.5, |
| "learning_rate": 1.2780000000000001e-05, |
| "loss": 11.0375, |
| "mean_token_accuracy": 0.802841005846858, |
| "num_tokens": 5329320.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.6868512833490967, |
| "epoch": 0.26, |
| "grad_norm": 55.0, |
| "learning_rate": 1.2980000000000001e-05, |
| "loss": 10.9356, |
| "mean_token_accuracy": 0.8048643987625838, |
| "num_tokens": 5412557.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.660436293296516, |
| "epoch": 0.264, |
| "grad_norm": 65.5, |
| "learning_rate": 1.3180000000000001e-05, |
| "loss": 10.8415, |
| "mean_token_accuracy": 0.8079600531607867, |
| "num_tokens": 5497259.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.7050647180527448, |
| "epoch": 0.268, |
| "grad_norm": 60.5, |
| "learning_rate": 1.3380000000000002e-05, |
| "loss": 11.106, |
| "mean_token_accuracy": 0.8046324852854013, |
| "num_tokens": 5576721.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.7028336159884929, |
| "epoch": 0.272, |
| "grad_norm": 61.25, |
| "learning_rate": 1.3580000000000002e-05, |
| "loss": 11.3741, |
| "mean_token_accuracy": 0.7989816222339868, |
| "num_tokens": 5658796.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.713030344620347, |
| "epoch": 0.276, |
| "grad_norm": 62.0, |
| "learning_rate": 1.378e-05, |
| "loss": 11.4372, |
| "mean_token_accuracy": 0.797571299597621, |
| "num_tokens": 5737499.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.6879976620897651, |
| "epoch": 0.28, |
| "grad_norm": 78.5, |
| "learning_rate": 1.398e-05, |
| "loss": 11.1153, |
| "mean_token_accuracy": 0.8056350216269493, |
| "num_tokens": 5819027.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_biology_entropy": 1.2951917058229447, |
| "eval_biology_loss": 1.374377727508545, |
| "eval_biology_mean_token_accuracy": 0.6666482761502266, |
| "eval_biology_num_tokens": 5819027.0, |
| "eval_biology_runtime": 35.3803, |
| "eval_biology_samples_per_second": 14.132, |
| "eval_biology_steps_per_second": 14.132, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_chemistry_entropy": 0.8508687050342559, |
| "eval_chemistry_loss": 0.8420527577400208, |
| "eval_chemistry_mean_token_accuracy": 0.7695601610541344, |
| "eval_chemistry_num_tokens": 5819027.0, |
| "eval_chemistry_runtime": 39.6948, |
| "eval_chemistry_samples_per_second": 12.596, |
| "eval_chemistry_steps_per_second": 12.596, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_math_entropy": 0.7296031129956245, |
| "eval_math_loss": 0.8581300377845764, |
| "eval_math_mean_token_accuracy": 0.7747315044403076, |
| "eval_math_num_tokens": 5819027.0, |
| "eval_math_runtime": 40.6002, |
| "eval_math_samples_per_second": 12.315, |
| "eval_math_steps_per_second": 12.315, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_physics_entropy": 0.7137228677272797, |
| "eval_physics_loss": 0.6899552941322327, |
| "eval_physics_mean_token_accuracy": 0.804570896744728, |
| "eval_physics_num_tokens": 5819027.0, |
| "eval_physics_runtime": 45.1753, |
| "eval_physics_samples_per_second": 11.068, |
| "eval_physics_steps_per_second": 11.068, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.7131443534046411, |
| "epoch": 0.284, |
| "grad_norm": 76.5, |
| "learning_rate": 1.418e-05, |
| "loss": 11.5042, |
| "mean_token_accuracy": 0.7973460745066404, |
| "num_tokens": 5898693.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.6842026851139963, |
| "epoch": 0.288, |
| "grad_norm": 58.5, |
| "learning_rate": 1.4380000000000001e-05, |
| "loss": 10.9569, |
| "mean_token_accuracy": 0.8062832679599523, |
| "num_tokens": 5980201.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.6580634312704206, |
| "epoch": 0.292, |
| "grad_norm": 58.0, |
| "learning_rate": 1.4580000000000001e-05, |
| "loss": 10.6812, |
| "mean_token_accuracy": 0.8109602797776461, |
| "num_tokens": 6059507.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.6885316792875529, |
| "epoch": 0.296, |
| "grad_norm": 59.0, |
| "learning_rate": 1.478e-05, |
| "loss": 11.1324, |
| "mean_token_accuracy": 0.8033004485070705, |
| "num_tokens": 6139830.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.6904184087179601, |
| "epoch": 0.3, |
| "grad_norm": 54.0, |
| "learning_rate": 1.498e-05, |
| "loss": 10.9676, |
| "mean_token_accuracy": 0.8058249101042747, |
| "num_tokens": 6218134.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.693754238076508, |
| "epoch": 0.304, |
| "grad_norm": 59.5, |
| "learning_rate": 1.5180000000000002e-05, |
| "loss": 11.1453, |
| "mean_token_accuracy": 0.804497017711401, |
| "num_tokens": 6298858.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.7230889040045441, |
| "epoch": 0.308, |
| "grad_norm": 66.5, |
| "learning_rate": 1.5380000000000002e-05, |
| "loss": 11.775, |
| "mean_token_accuracy": 0.7913905128836631, |
| "num_tokens": 6375761.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.6630848026834428, |
| "epoch": 0.312, |
| "grad_norm": 50.0, |
| "learning_rate": 1.5580000000000003e-05, |
| "loss": 10.6675, |
| "mean_token_accuracy": 0.8106919646263122, |
| "num_tokens": 6456502.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.6884183536283672, |
| "epoch": 0.316, |
| "grad_norm": 65.5, |
| "learning_rate": 1.578e-05, |
| "loss": 11.2036, |
| "mean_token_accuracy": 0.8040056221187115, |
| "num_tokens": 6537521.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.7094144577160477, |
| "epoch": 0.32, |
| "grad_norm": 51.75, |
| "learning_rate": 1.5980000000000003e-05, |
| "loss": 11.3893, |
| "mean_token_accuracy": 0.7988939873874188, |
| "num_tokens": 6622798.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_biology_entropy": 1.272662544965744, |
| "eval_biology_loss": 1.3795855045318604, |
| "eval_biology_mean_token_accuracy": 0.6654499787688255, |
| "eval_biology_num_tokens": 6622798.0, |
| "eval_biology_runtime": 35.1835, |
| "eval_biology_samples_per_second": 14.211, |
| "eval_biology_steps_per_second": 14.211, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_chemistry_entropy": 0.8212787560224533, |
| "eval_chemistry_loss": 0.8387787938117981, |
| "eval_chemistry_mean_token_accuracy": 0.7721875888109208, |
| "eval_chemistry_num_tokens": 6622798.0, |
| "eval_chemistry_runtime": 39.5827, |
| "eval_chemistry_samples_per_second": 12.632, |
| "eval_chemistry_steps_per_second": 12.632, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_math_entropy": 0.6975619449019432, |
| "eval_math_loss": 0.8566721081733704, |
| "eval_math_mean_token_accuracy": 0.7762556113004685, |
| "eval_math_num_tokens": 6622798.0, |
| "eval_math_runtime": 40.4554, |
| "eval_math_samples_per_second": 12.359, |
| "eval_math_steps_per_second": 12.359, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_physics_entropy": 0.6843295809030533, |
| "eval_physics_loss": 0.6862691640853882, |
| "eval_physics_mean_token_accuracy": 0.8047665995955467, |
| "eval_physics_num_tokens": 6622798.0, |
| "eval_physics_runtime": 45.1382, |
| "eval_physics_samples_per_second": 11.077, |
| "eval_physics_steps_per_second": 11.077, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.6872260123491287, |
| "epoch": 0.324, |
| "grad_norm": 61.75, |
| "learning_rate": 1.618e-05, |
| "loss": 11.1453, |
| "mean_token_accuracy": 0.8037573281675577, |
| "num_tokens": 6699373.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.7004622181877493, |
| "epoch": 0.328, |
| "grad_norm": 53.0, |
| "learning_rate": 1.638e-05, |
| "loss": 11.2569, |
| "mean_token_accuracy": 0.8005565378814936, |
| "num_tokens": 6782985.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.683347325026989, |
| "epoch": 0.332, |
| "grad_norm": 67.0, |
| "learning_rate": 1.658e-05, |
| "loss": 10.9209, |
| "mean_token_accuracy": 0.8052662838250398, |
| "num_tokens": 6868578.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.6550024008378387, |
| "epoch": 0.336, |
| "grad_norm": 49.0, |
| "learning_rate": 1.6780000000000002e-05, |
| "loss": 10.4463, |
| "mean_token_accuracy": 0.8156119327992201, |
| "num_tokens": 6953611.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.6940796528942883, |
| "epoch": 0.34, |
| "grad_norm": 60.75, |
| "learning_rate": 1.698e-05, |
| "loss": 11.4328, |
| "mean_token_accuracy": 0.7994465328752994, |
| "num_tokens": 7037831.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.6509441762231291, |
| "epoch": 0.344, |
| "grad_norm": 68.0, |
| "learning_rate": 1.718e-05, |
| "loss": 10.5903, |
| "mean_token_accuracy": 0.8100398641079665, |
| "num_tokens": 7121949.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.68049411540851, |
| "epoch": 0.348, |
| "grad_norm": 50.75, |
| "learning_rate": 1.7380000000000003e-05, |
| "loss": 10.7995, |
| "mean_token_accuracy": 0.8092381667345763, |
| "num_tokens": 7206056.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.6681747000664473, |
| "epoch": 0.352, |
| "grad_norm": 59.0, |
| "learning_rate": 1.758e-05, |
| "loss": 10.7902, |
| "mean_token_accuracy": 0.8085832469165325, |
| "num_tokens": 7290378.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.6910556216724217, |
| "epoch": 0.356, |
| "grad_norm": 46.5, |
| "learning_rate": 1.7780000000000003e-05, |
| "loss": 11.072, |
| "mean_token_accuracy": 0.8025941159576178, |
| "num_tokens": 7367952.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.6846336699090898, |
| "epoch": 0.36, |
| "grad_norm": 69.0, |
| "learning_rate": 1.798e-05, |
| "loss": 10.9941, |
| "mean_token_accuracy": 0.8069840248674154, |
| "num_tokens": 7452920.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_biology_entropy": 1.3079615205526351, |
| "eval_biology_loss": 1.3845115900039673, |
| "eval_biology_mean_token_accuracy": 0.6659645406007767, |
| "eval_biology_num_tokens": 7452920.0, |
| "eval_biology_runtime": 35.2058, |
| "eval_biology_samples_per_second": 14.202, |
| "eval_biology_steps_per_second": 14.202, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_chemistry_entropy": 0.855868073105812, |
| "eval_chemistry_loss": 0.8524179458618164, |
| "eval_chemistry_mean_token_accuracy": 0.7686776904463768, |
| "eval_chemistry_num_tokens": 7452920.0, |
| "eval_chemistry_runtime": 39.6971, |
| "eval_chemistry_samples_per_second": 12.595, |
| "eval_chemistry_steps_per_second": 12.595, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_math_entropy": 0.7238874210417271, |
| "eval_math_loss": 0.8637869954109192, |
| "eval_math_mean_token_accuracy": 0.774171804189682, |
| "eval_math_num_tokens": 7452920.0, |
| "eval_math_runtime": 40.502, |
| "eval_math_samples_per_second": 12.345, |
| "eval_math_steps_per_second": 12.345, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_physics_entropy": 0.703471056163311, |
| "eval_physics_loss": 0.6876726150512695, |
| "eval_physics_mean_token_accuracy": 0.8049070924520493, |
| "eval_physics_num_tokens": 7452920.0, |
| "eval_physics_runtime": 45.1347, |
| "eval_physics_samples_per_second": 11.078, |
| "eval_physics_steps_per_second": 11.078, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.6624960891902447, |
| "epoch": 0.364, |
| "grad_norm": 50.25, |
| "learning_rate": 1.8180000000000002e-05, |
| "loss": 10.6947, |
| "mean_token_accuracy": 0.8089043792337179, |
| "num_tokens": 7535961.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 0.6663541577756404, |
| "epoch": 0.368, |
| "grad_norm": 51.0, |
| "learning_rate": 1.8380000000000004e-05, |
| "loss": 10.5684, |
| "mean_token_accuracy": 0.810727647319436, |
| "num_tokens": 7621082.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 0.6552547904662788, |
| "epoch": 0.372, |
| "grad_norm": 51.5, |
| "learning_rate": 1.858e-05, |
| "loss": 10.6444, |
| "mean_token_accuracy": 0.8090339493006468, |
| "num_tokens": 7705651.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 0.7489686900749802, |
| "epoch": 0.376, |
| "grad_norm": 51.5, |
| "learning_rate": 1.878e-05, |
| "loss": 12.0319, |
| "mean_token_accuracy": 0.7858695086091757, |
| "num_tokens": 7787036.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 0.6922270046547055, |
| "epoch": 0.38, |
| "grad_norm": 63.0, |
| "learning_rate": 1.898e-05, |
| "loss": 11.1499, |
| "mean_token_accuracy": 0.7991227209568024, |
| "num_tokens": 7869437.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.6693172385916114, |
| "epoch": 0.384, |
| "grad_norm": 45.75, |
| "learning_rate": 1.918e-05, |
| "loss": 10.7571, |
| "mean_token_accuracy": 0.8078656267374754, |
| "num_tokens": 7955570.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 0.6446146180853247, |
| "epoch": 0.388, |
| "grad_norm": 43.5, |
| "learning_rate": 1.938e-05, |
| "loss": 10.4611, |
| "mean_token_accuracy": 0.8115016505122185, |
| "num_tokens": 8038818.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 0.6791700626723468, |
| "epoch": 0.392, |
| "grad_norm": 45.0, |
| "learning_rate": 1.9580000000000002e-05, |
| "loss": 10.8502, |
| "mean_token_accuracy": 0.8048314619809389, |
| "num_tokens": 8123527.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 0.684117188770324, |
| "epoch": 0.396, |
| "grad_norm": 48.75, |
| "learning_rate": 1.978e-05, |
| "loss": 10.9286, |
| "mean_token_accuracy": 0.8045736275613308, |
| "num_tokens": 8206501.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 0.6638183539733291, |
| "epoch": 0.4, |
| "grad_norm": 45.25, |
| "learning_rate": 1.9980000000000002e-05, |
| "loss": 10.7878, |
| "mean_token_accuracy": 0.8090838421136141, |
| "num_tokens": 8291049.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_biology_entropy": 1.3014859555363656, |
| "eval_biology_loss": 1.4013315439224243, |
| "eval_biology_mean_token_accuracy": 0.6621385813355446, |
| "eval_biology_num_tokens": 8291049.0, |
| "eval_biology_runtime": 35.3423, |
| "eval_biology_samples_per_second": 14.147, |
| "eval_biology_steps_per_second": 14.147, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_chemistry_entropy": 0.8515431408882141, |
| "eval_chemistry_loss": 0.8530916571617126, |
| "eval_chemistry_mean_token_accuracy": 0.7688064026236534, |
| "eval_chemistry_num_tokens": 8291049.0, |
| "eval_chemistry_runtime": 39.7131, |
| "eval_chemistry_samples_per_second": 12.59, |
| "eval_chemistry_steps_per_second": 12.59, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_math_entropy": 0.7349339348077774, |
| "eval_math_loss": 0.8596640825271606, |
| "eval_math_mean_token_accuracy": 0.7750666145086288, |
| "eval_math_num_tokens": 8291049.0, |
| "eval_math_runtime": 40.5711, |
| "eval_math_samples_per_second": 12.324, |
| "eval_math_steps_per_second": 12.324, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_physics_entropy": 0.698657899916172, |
| "eval_physics_loss": 0.690846860408783, |
| "eval_physics_mean_token_accuracy": 0.8048570597171784, |
| "eval_physics_num_tokens": 8291049.0, |
| "eval_physics_runtime": 45.18, |
| "eval_physics_samples_per_second": 11.067, |
| "eval_physics_steps_per_second": 11.067, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.6724585631862283, |
| "epoch": 0.404, |
| "grad_norm": 47.0, |
| "learning_rate": 1.9980000000000002e-05, |
| "loss": 10.7513, |
| "mean_token_accuracy": 0.8090190943330526, |
| "num_tokens": 8373687.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 0.6880609506741167, |
| "epoch": 0.408, |
| "grad_norm": 49.0, |
| "learning_rate": 1.995777777777778e-05, |
| "loss": 11.0507, |
| "mean_token_accuracy": 0.8037724006921053, |
| "num_tokens": 8459795.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 0.6609848150983453, |
| "epoch": 0.412, |
| "grad_norm": 50.75, |
| "learning_rate": 1.9935555555555557e-05, |
| "loss": 10.803, |
| "mean_token_accuracy": 0.8078120674937963, |
| "num_tokens": 8544948.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 0.6650119775906205, |
| "epoch": 0.416, |
| "grad_norm": 49.25, |
| "learning_rate": 1.9913333333333335e-05, |
| "loss": 10.794, |
| "mean_token_accuracy": 0.8062687937170268, |
| "num_tokens": 8627310.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 0.7647646913304925, |
| "epoch": 0.42, |
| "grad_norm": 50.25, |
| "learning_rate": 1.9891111111111112e-05, |
| "loss": 12.2348, |
| "mean_token_accuracy": 0.7883469216525555, |
| "num_tokens": 8707798.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.6614232028834521, |
| "epoch": 0.424, |
| "grad_norm": 46.0, |
| "learning_rate": 1.986888888888889e-05, |
| "loss": 10.6404, |
| "mean_token_accuracy": 0.8107621461153031, |
| "num_tokens": 8792574.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 0.6635355862788856, |
| "epoch": 0.428, |
| "grad_norm": 54.25, |
| "learning_rate": 1.9846666666666668e-05, |
| "loss": 10.7408, |
| "mean_token_accuracy": 0.8067193511873484, |
| "num_tokens": 8878637.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 0.6831195020116866, |
| "epoch": 0.432, |
| "grad_norm": 56.75, |
| "learning_rate": 1.9824444444444445e-05, |
| "loss": 10.9817, |
| "mean_token_accuracy": 0.8036571219563484, |
| "num_tokens": 8958371.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 0.6557174487970769, |
| "epoch": 0.436, |
| "grad_norm": 56.25, |
| "learning_rate": 1.9802222222222226e-05, |
| "loss": 10.5087, |
| "mean_token_accuracy": 0.8101301193237305, |
| "num_tokens": 9040649.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 0.6296142281033099, |
| "epoch": 0.44, |
| "grad_norm": 46.25, |
| "learning_rate": 1.978e-05, |
| "loss": 10.1617, |
| "mean_token_accuracy": 0.8164261173456907, |
| "num_tokens": 9125564.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_biology_entropy": 1.2857338542938233, |
| "eval_biology_loss": 1.4026042222976685, |
| "eval_biology_mean_token_accuracy": 0.6611523522734642, |
| "eval_biology_num_tokens": 9125564.0, |
| "eval_biology_runtime": 35.3074, |
| "eval_biology_samples_per_second": 14.161, |
| "eval_biology_steps_per_second": 14.161, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_chemistry_entropy": 0.8301562021374702, |
| "eval_chemistry_loss": 0.8592454195022583, |
| "eval_chemistry_mean_token_accuracy": 0.7674569791555405, |
| "eval_chemistry_num_tokens": 9125564.0, |
| "eval_chemistry_runtime": 39.7025, |
| "eval_chemistry_samples_per_second": 12.594, |
| "eval_chemistry_steps_per_second": 12.594, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_math_entropy": 0.704224185705185, |
| "eval_math_loss": 0.8685066103935242, |
| "eval_math_mean_token_accuracy": 0.7726707045435905, |
| "eval_math_num_tokens": 9125564.0, |
| "eval_math_runtime": 40.5031, |
| "eval_math_samples_per_second": 12.345, |
| "eval_math_steps_per_second": 12.345, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_physics_entropy": 0.676539529800415, |
| "eval_physics_loss": 0.6832760572433472, |
| "eval_physics_mean_token_accuracy": 0.8052293303608894, |
| "eval_physics_num_tokens": 9125564.0, |
| "eval_physics_runtime": 45.1101, |
| "eval_physics_samples_per_second": 11.084, |
| "eval_physics_steps_per_second": 11.084, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.7054770017042756, |
| "epoch": 0.444, |
| "grad_norm": 47.75, |
| "learning_rate": 1.975777777777778e-05, |
| "loss": 11.3801, |
| "mean_token_accuracy": 0.8028026439249516, |
| "num_tokens": 9210443.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 0.6552120961248875, |
| "epoch": 0.448, |
| "grad_norm": 42.0, |
| "learning_rate": 1.9735555555555556e-05, |
| "loss": 10.7148, |
| "mean_token_accuracy": 0.8113164242357016, |
| "num_tokens": 9294388.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 0.6474918988533318, |
| "epoch": 0.452, |
| "grad_norm": 49.0, |
| "learning_rate": 1.9713333333333337e-05, |
| "loss": 10.1143, |
| "mean_token_accuracy": 0.8196653757244349, |
| "num_tokens": 9371203.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 0.6594600110314787, |
| "epoch": 0.456, |
| "grad_norm": 43.5, |
| "learning_rate": 1.969111111111111e-05, |
| "loss": 10.7859, |
| "mean_token_accuracy": 0.806324940547347, |
| "num_tokens": 9455428.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 0.6459505766630173, |
| "epoch": 0.46, |
| "grad_norm": 41.25, |
| "learning_rate": 1.9668888888888892e-05, |
| "loss": 10.2758, |
| "mean_token_accuracy": 0.8145925845950842, |
| "num_tokens": 9539605.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.6633252296596766, |
| "epoch": 0.464, |
| "grad_norm": 46.75, |
| "learning_rate": 1.9646666666666666e-05, |
| "loss": 10.746, |
| "mean_token_accuracy": 0.8067185960710048, |
| "num_tokens": 9620366.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 0.6536956983618438, |
| "epoch": 0.468, |
| "grad_norm": 54.75, |
| "learning_rate": 1.9624444444444447e-05, |
| "loss": 10.5255, |
| "mean_token_accuracy": 0.8116643182933331, |
| "num_tokens": 9706621.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 0.6528704442083836, |
| "epoch": 0.472, |
| "grad_norm": 42.5, |
| "learning_rate": 1.9602222222222225e-05, |
| "loss": 10.4167, |
| "mean_token_accuracy": 0.8110667478293181, |
| "num_tokens": 9788925.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 0.6303915046155453, |
| "epoch": 0.476, |
| "grad_norm": 40.75, |
| "learning_rate": 1.9580000000000002e-05, |
| "loss": 10.2211, |
| "mean_token_accuracy": 0.8153577871620655, |
| "num_tokens": 9869908.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 0.7140287417918444, |
| "epoch": 0.48, |
| "grad_norm": 50.5, |
| "learning_rate": 1.955777777777778e-05, |
| "loss": 11.4393, |
| "mean_token_accuracy": 0.7977926902472973, |
| "num_tokens": 9955431.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_biology_entropy": 1.2901287813782691, |
| "eval_biology_loss": 1.4074944257736206, |
| "eval_biology_mean_token_accuracy": 0.6630856924653054, |
| "eval_biology_num_tokens": 9955431.0, |
| "eval_biology_runtime": 35.1485, |
| "eval_biology_samples_per_second": 14.225, |
| "eval_biology_steps_per_second": 14.225, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_chemistry_entropy": 0.8402542336285115, |
| "eval_chemistry_loss": 0.8475250005722046, |
| "eval_chemistry_mean_token_accuracy": 0.7706258528828621, |
| "eval_chemistry_num_tokens": 9955431.0, |
| "eval_chemistry_runtime": 39.5963, |
| "eval_chemistry_samples_per_second": 12.627, |
| "eval_chemistry_steps_per_second": 12.627, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_math_entropy": 0.7095566186904907, |
| "eval_math_loss": 0.8719534873962402, |
| "eval_math_mean_token_accuracy": 0.7730017136335373, |
| "eval_math_num_tokens": 9955431.0, |
| "eval_math_runtime": 40.4499, |
| "eval_math_samples_per_second": 12.361, |
| "eval_math_steps_per_second": 12.361, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_physics_entropy": 0.6804338894784451, |
| "eval_physics_loss": 0.6772474646568298, |
| "eval_physics_mean_token_accuracy": 0.8075065380334854, |
| "eval_physics_num_tokens": 9955431.0, |
| "eval_physics_runtime": 45.0788, |
| "eval_physics_samples_per_second": 11.092, |
| "eval_physics_steps_per_second": 11.092, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.6472635091282427, |
| "epoch": 0.484, |
| "grad_norm": 50.75, |
| "learning_rate": 1.9535555555555557e-05, |
| "loss": 10.4858, |
| "mean_token_accuracy": 0.8127345737069845, |
| "num_tokens": 10038293.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 0.6718290301039815, |
| "epoch": 0.488, |
| "grad_norm": 43.25, |
| "learning_rate": 1.9513333333333335e-05, |
| "loss": 10.7595, |
| "mean_token_accuracy": 0.8104257199913263, |
| "num_tokens": 10119599.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 0.7013039434328675, |
| "epoch": 0.492, |
| "grad_norm": 49.25, |
| "learning_rate": 1.9491111111111113e-05, |
| "loss": 11.2505, |
| "mean_token_accuracy": 0.8000239260494709, |
| "num_tokens": 10204514.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 0.6948929887264967, |
| "epoch": 0.496, |
| "grad_norm": 42.25, |
| "learning_rate": 1.946888888888889e-05, |
| "loss": 11.0562, |
| "mean_token_accuracy": 0.8022828463464975, |
| "num_tokens": 10289883.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 0.6491774883121252, |
| "epoch": 0.5, |
| "grad_norm": 48.25, |
| "learning_rate": 1.9446666666666668e-05, |
| "loss": 10.5893, |
| "mean_token_accuracy": 0.8121375739574432, |
| "num_tokens": 10368762.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.6618938606232405, |
| "epoch": 0.504, |
| "grad_norm": 43.5, |
| "learning_rate": 1.9424444444444446e-05, |
| "loss": 10.5939, |
| "mean_token_accuracy": 0.8118096552789211, |
| "num_tokens": 10454683.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 0.6799033954739571, |
| "epoch": 0.508, |
| "grad_norm": 47.0, |
| "learning_rate": 1.9402222222222223e-05, |
| "loss": 11.031, |
| "mean_token_accuracy": 0.804159976914525, |
| "num_tokens": 10539515.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 0.7304276229813695, |
| "epoch": 0.512, |
| "grad_norm": 51.5, |
| "learning_rate": 1.938e-05, |
| "loss": 11.6009, |
| "mean_token_accuracy": 0.7962873011827469, |
| "num_tokens": 10619468.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 0.6799104714766144, |
| "epoch": 0.516, |
| "grad_norm": 45.75, |
| "learning_rate": 1.935777777777778e-05, |
| "loss": 11.0138, |
| "mean_token_accuracy": 0.805281289294362, |
| "num_tokens": 10698439.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 0.6859343230724335, |
| "epoch": 0.52, |
| "grad_norm": 42.25, |
| "learning_rate": 1.9335555555555556e-05, |
| "loss": 11.027, |
| "mean_token_accuracy": 0.8035755015909671, |
| "num_tokens": 10781285.0, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_biology_entropy": 1.2939175048470497, |
| "eval_biology_loss": 1.4010000228881836, |
| "eval_biology_mean_token_accuracy": 0.6629679874181748, |
| "eval_biology_num_tokens": 10781285.0, |
| "eval_biology_runtime": 35.2822, |
| "eval_biology_samples_per_second": 14.171, |
| "eval_biology_steps_per_second": 14.171, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_chemistry_entropy": 0.8264291672706604, |
| "eval_chemistry_loss": 0.847792387008667, |
| "eval_chemistry_mean_token_accuracy": 0.7705023067593575, |
| "eval_chemistry_num_tokens": 10781285.0, |
| "eval_chemistry_runtime": 39.6216, |
| "eval_chemistry_samples_per_second": 12.619, |
| "eval_chemistry_steps_per_second": 12.619, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_math_entropy": 0.7105307767689228, |
| "eval_math_loss": 0.8610548973083496, |
| "eval_math_mean_token_accuracy": 0.7741031144857407, |
| "eval_math_num_tokens": 10781285.0, |
| "eval_math_runtime": 40.4357, |
| "eval_math_samples_per_second": 12.365, |
| "eval_math_steps_per_second": 12.365, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_physics_entropy": 0.6724484626352787, |
| "eval_physics_loss": 0.6681262254714966, |
| "eval_physics_mean_token_accuracy": 0.8100028432011604, |
| "eval_physics_num_tokens": 10781285.0, |
| "eval_physics_runtime": 45.0631, |
| "eval_physics_samples_per_second": 11.096, |
| "eval_physics_steps_per_second": 11.096, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.6645524255931378, |
| "epoch": 0.524, |
| "grad_norm": 47.0, |
| "learning_rate": 1.9313333333333334e-05, |
| "loss": 10.7825, |
| "mean_token_accuracy": 0.8092559453099966, |
| "num_tokens": 10864773.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 0.6470350125804544, |
| "epoch": 0.528, |
| "grad_norm": 41.0, |
| "learning_rate": 1.9291111111111115e-05, |
| "loss": 10.3184, |
| "mean_token_accuracy": 0.815019316598773, |
| "num_tokens": 10944904.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 0.6757032671943307, |
| "epoch": 0.532, |
| "grad_norm": 47.75, |
| "learning_rate": 1.926888888888889e-05, |
| "loss": 10.8658, |
| "mean_token_accuracy": 0.8063097450882196, |
| "num_tokens": 11023958.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 0.6243293879553675, |
| "epoch": 0.536, |
| "grad_norm": 46.25, |
| "learning_rate": 1.924666666666667e-05, |
| "loss": 10.1411, |
| "mean_token_accuracy": 0.8193823467940092, |
| "num_tokens": 11106538.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 0.6877710536122322, |
| "epoch": 0.54, |
| "grad_norm": 54.5, |
| "learning_rate": 1.9224444444444444e-05, |
| "loss": 10.9827, |
| "mean_token_accuracy": 0.8047556940466165, |
| "num_tokens": 11187142.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.7018949103541672, |
| "epoch": 0.544, |
| "grad_norm": 55.75, |
| "learning_rate": 1.9202222222222225e-05, |
| "loss": 11.3787, |
| "mean_token_accuracy": 0.7996319092810154, |
| "num_tokens": 11266409.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 0.6630384393967688, |
| "epoch": 0.548, |
| "grad_norm": 50.75, |
| "learning_rate": 1.918e-05, |
| "loss": 10.6384, |
| "mean_token_accuracy": 0.8089293787255883, |
| "num_tokens": 11350094.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 0.6659614780917764, |
| "epoch": 0.552, |
| "grad_norm": 45.75, |
| "learning_rate": 1.915777777777778e-05, |
| "loss": 10.7485, |
| "mean_token_accuracy": 0.8104357924312353, |
| "num_tokens": 11438391.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 0.6783489585854113, |
| "epoch": 0.556, |
| "grad_norm": 54.0, |
| "learning_rate": 1.9135555555555555e-05, |
| "loss": 10.738, |
| "mean_token_accuracy": 0.8090345006436109, |
| "num_tokens": 11521583.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 0.6332698877900839, |
| "epoch": 0.56, |
| "grad_norm": 42.0, |
| "learning_rate": 1.9113333333333336e-05, |
| "loss": 10.1535, |
| "mean_token_accuracy": 0.817741920426488, |
| "num_tokens": 11605544.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_biology_entropy": 1.2966757586598396, |
| "eval_biology_loss": 1.4016809463500977, |
| "eval_biology_mean_token_accuracy": 0.6630619642138481, |
| "eval_biology_num_tokens": 11605544.0, |
| "eval_biology_runtime": 35.3173, |
| "eval_biology_samples_per_second": 14.157, |
| "eval_biology_steps_per_second": 14.157, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_chemistry_entropy": 0.8152842739224434, |
| "eval_chemistry_loss": 0.8491419553756714, |
| "eval_chemistry_mean_token_accuracy": 0.7716290903687477, |
| "eval_chemistry_num_tokens": 11605544.0, |
| "eval_chemistry_runtime": 39.6109, |
| "eval_chemistry_samples_per_second": 12.623, |
| "eval_chemistry_steps_per_second": 12.623, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_math_entropy": 0.7092237346470356, |
| "eval_math_loss": 0.8697728514671326, |
| "eval_math_mean_token_accuracy": 0.7739188714027405, |
| "eval_math_num_tokens": 11605544.0, |
| "eval_math_runtime": 40.4481, |
| "eval_math_samples_per_second": 12.362, |
| "eval_math_steps_per_second": 12.362, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_physics_entropy": 0.6652475365400314, |
| "eval_physics_loss": 0.6614710688591003, |
| "eval_physics_mean_token_accuracy": 0.8117705038189889, |
| "eval_physics_num_tokens": 11605544.0, |
| "eval_physics_runtime": 45.1827, |
| "eval_physics_samples_per_second": 11.066, |
| "eval_physics_steps_per_second": 11.066, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.6269684578292072, |
| "epoch": 0.564, |
| "grad_norm": 42.5, |
| "learning_rate": 1.9091111111111113e-05, |
| "loss": 10.2481, |
| "mean_token_accuracy": 0.8174567829817534, |
| "num_tokens": 11686173.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 0.6821280302479863, |
| "epoch": 0.568, |
| "grad_norm": 38.25, |
| "learning_rate": 1.906888888888889e-05, |
| "loss": 10.6848, |
| "mean_token_accuracy": 0.8115028716623783, |
| "num_tokens": 11765430.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 0.6392442825250327, |
| "epoch": 0.572, |
| "grad_norm": 44.0, |
| "learning_rate": 1.904666666666667e-05, |
| "loss": 10.5018, |
| "mean_token_accuracy": 0.8134302724152803, |
| "num_tokens": 11850973.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 0.6551524167880416, |
| "epoch": 0.576, |
| "grad_norm": 56.25, |
| "learning_rate": 1.9024444444444446e-05, |
| "loss": 10.4141, |
| "mean_token_accuracy": 0.8127408139407635, |
| "num_tokens": 11931715.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 0.6323688972741366, |
| "epoch": 0.58, |
| "grad_norm": 47.75, |
| "learning_rate": 1.9002222222222224e-05, |
| "loss": 9.9927, |
| "mean_token_accuracy": 0.8190583731979132, |
| "num_tokens": 12012155.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.6468079431913794, |
| "epoch": 0.584, |
| "grad_norm": 44.25, |
| "learning_rate": 1.898e-05, |
| "loss": 10.5496, |
| "mean_token_accuracy": 0.8117645151913166, |
| "num_tokens": 12093686.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 0.6574975445866584, |
| "epoch": 0.588, |
| "grad_norm": 46.5, |
| "learning_rate": 1.895777777777778e-05, |
| "loss": 10.4738, |
| "mean_token_accuracy": 0.81148545704782, |
| "num_tokens": 12177581.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 0.6759683048352599, |
| "epoch": 0.592, |
| "grad_norm": 46.25, |
| "learning_rate": 1.8935555555555556e-05, |
| "loss": 10.844, |
| "mean_token_accuracy": 0.8061960492283106, |
| "num_tokens": 12257243.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 0.6535733859054744, |
| "epoch": 0.596, |
| "grad_norm": 58.75, |
| "learning_rate": 1.8913333333333334e-05, |
| "loss": 10.5604, |
| "mean_token_accuracy": 0.8106869570910931, |
| "num_tokens": 12338544.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 0.635299691837281, |
| "epoch": 0.6, |
| "grad_norm": 45.25, |
| "learning_rate": 1.8891111111111115e-05, |
| "loss": 10.1003, |
| "mean_token_accuracy": 0.8157124288380146, |
| "num_tokens": 12422008.0, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_biology_entropy": 1.2644084550142287, |
| "eval_biology_loss": 1.403598666191101, |
| "eval_biology_mean_token_accuracy": 0.662936574101448, |
| "eval_biology_num_tokens": 12422008.0, |
| "eval_biology_runtime": 35.0607, |
| "eval_biology_samples_per_second": 14.261, |
| "eval_biology_steps_per_second": 14.261, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_chemistry_entropy": 0.7927452449202538, |
| "eval_chemistry_loss": 0.8444129824638367, |
| "eval_chemistry_mean_token_accuracy": 0.7716013901829719, |
| "eval_chemistry_num_tokens": 12422008.0, |
| "eval_chemistry_runtime": 39.6183, |
| "eval_chemistry_samples_per_second": 12.62, |
| "eval_chemistry_steps_per_second": 12.62, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_math_entropy": 0.6911805932819843, |
| "eval_math_loss": 0.8791993260383606, |
| "eval_math_mean_token_accuracy": 0.7729427699446678, |
| "eval_math_num_tokens": 12422008.0, |
| "eval_math_runtime": 40.5514, |
| "eval_math_samples_per_second": 12.33, |
| "eval_math_steps_per_second": 12.33, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_physics_entropy": 0.635497625797987, |
| "eval_physics_loss": 0.6566235423088074, |
| "eval_physics_mean_token_accuracy": 0.8124136482477188, |
| "eval_physics_num_tokens": 12422008.0, |
| "eval_physics_runtime": 45.1105, |
| "eval_physics_samples_per_second": 11.084, |
| "eval_physics_steps_per_second": 11.084, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.6438517822884023, |
| "epoch": 0.604, |
| "grad_norm": 46.25, |
| "learning_rate": 1.886888888888889e-05, |
| "loss": 10.4253, |
| "mean_token_accuracy": 0.8152689874172211, |
| "num_tokens": 12505134.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 0.6165852569974959, |
| "epoch": 0.608, |
| "grad_norm": 50.25, |
| "learning_rate": 1.884666666666667e-05, |
| "loss": 9.8857, |
| "mean_token_accuracy": 0.8216613974422217, |
| "num_tokens": 12583154.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 0.6570021582767367, |
| "epoch": 0.612, |
| "grad_norm": 42.75, |
| "learning_rate": 1.8824444444444445e-05, |
| "loss": 10.4566, |
| "mean_token_accuracy": 0.8129478100687265, |
| "num_tokens": 12666601.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 0.6499744065105915, |
| "epoch": 0.616, |
| "grad_norm": 42.5, |
| "learning_rate": 1.8802222222222226e-05, |
| "loss": 10.3697, |
| "mean_token_accuracy": 0.8139124307781458, |
| "num_tokens": 12746458.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 0.6602890061214566, |
| "epoch": 0.62, |
| "grad_norm": 39.0, |
| "learning_rate": 1.878e-05, |
| "loss": 10.7086, |
| "mean_token_accuracy": 0.8104711420834064, |
| "num_tokens": 12831572.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.6643684912472964, |
| "epoch": 0.624, |
| "grad_norm": 47.75, |
| "learning_rate": 1.875777777777778e-05, |
| "loss": 10.5879, |
| "mean_token_accuracy": 0.8116141181439162, |
| "num_tokens": 12905392.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 0.6584846514277161, |
| "epoch": 0.628, |
| "grad_norm": 43.75, |
| "learning_rate": 1.873555555555556e-05, |
| "loss": 10.5432, |
| "mean_token_accuracy": 0.8107300482690334, |
| "num_tokens": 12986513.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 0.638776770234108, |
| "epoch": 0.632, |
| "grad_norm": 39.5, |
| "learning_rate": 1.8713333333333336e-05, |
| "loss": 10.2261, |
| "mean_token_accuracy": 0.814822031930089, |
| "num_tokens": 13071058.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 0.6551781664602458, |
| "epoch": 0.636, |
| "grad_norm": 44.0, |
| "learning_rate": 1.8691111111111114e-05, |
| "loss": 10.5182, |
| "mean_token_accuracy": 0.8119142647832632, |
| "num_tokens": 13151842.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 0.7266039110720157, |
| "epoch": 0.64, |
| "grad_norm": 46.75, |
| "learning_rate": 1.866888888888889e-05, |
| "loss": 11.6713, |
| "mean_token_accuracy": 0.7968564338982105, |
| "num_tokens": 13232198.0, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_biology_entropy": 1.3351151769161225, |
| "eval_biology_loss": 1.3962006568908691, |
| "eval_biology_mean_token_accuracy": 0.6624402161240578, |
| "eval_biology_num_tokens": 13232198.0, |
| "eval_biology_runtime": 35.2387, |
| "eval_biology_samples_per_second": 14.189, |
| "eval_biology_steps_per_second": 14.189, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_chemistry_entropy": 0.8378922098278999, |
| "eval_chemistry_loss": 0.8399096727371216, |
| "eval_chemistry_mean_token_accuracy": 0.771498102247715, |
| "eval_chemistry_num_tokens": 13232198.0, |
| "eval_chemistry_runtime": 39.6463, |
| "eval_chemistry_samples_per_second": 12.612, |
| "eval_chemistry_steps_per_second": 12.612, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_math_entropy": 0.7215032837092876, |
| "eval_math_loss": 0.8692191243171692, |
| "eval_math_mean_token_accuracy": 0.7733984060287475, |
| "eval_math_num_tokens": 13232198.0, |
| "eval_math_runtime": 40.5046, |
| "eval_math_samples_per_second": 12.344, |
| "eval_math_steps_per_second": 12.344, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_physics_entropy": 0.6693824680745601, |
| "eval_physics_loss": 0.6483619213104248, |
| "eval_physics_mean_token_accuracy": 0.8146560984253883, |
| "eval_physics_num_tokens": 13232198.0, |
| "eval_physics_runtime": 45.1205, |
| "eval_physics_samples_per_second": 11.081, |
| "eval_physics_steps_per_second": 11.081, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.6329503210261465, |
| "epoch": 0.644, |
| "grad_norm": 41.5, |
| "learning_rate": 1.864666666666667e-05, |
| "loss": 10.1519, |
| "mean_token_accuracy": 0.8150339797139168, |
| "num_tokens": 13318037.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 0.6718782410956919, |
| "epoch": 0.648, |
| "grad_norm": 48.25, |
| "learning_rate": 1.8624444444444446e-05, |
| "loss": 10.6876, |
| "mean_token_accuracy": 0.8110412795096635, |
| "num_tokens": 13401064.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 0.6298892620950938, |
| "epoch": 0.652, |
| "grad_norm": 52.0, |
| "learning_rate": 1.8602222222222224e-05, |
| "loss": 10.2865, |
| "mean_token_accuracy": 0.8168573569506407, |
| "num_tokens": 13488222.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 0.6405643708072603, |
| "epoch": 0.656, |
| "grad_norm": 39.75, |
| "learning_rate": 1.858e-05, |
| "loss": 10.0944, |
| "mean_token_accuracy": 0.8184370543807745, |
| "num_tokens": 13575902.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 0.6571455264464021, |
| "epoch": 0.66, |
| "grad_norm": 41.25, |
| "learning_rate": 1.855777777777778e-05, |
| "loss": 10.5153, |
| "mean_token_accuracy": 0.8104129206389189, |
| "num_tokens": 13655826.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.6566264102235436, |
| "epoch": 0.664, |
| "grad_norm": 55.5, |
| "learning_rate": 1.8535555555555557e-05, |
| "loss": 10.5224, |
| "mean_token_accuracy": 0.8120165556669235, |
| "num_tokens": 13733192.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 0.6292093011550606, |
| "epoch": 0.668, |
| "grad_norm": 37.0, |
| "learning_rate": 1.8513333333333335e-05, |
| "loss": 10.0179, |
| "mean_token_accuracy": 0.8215251605957746, |
| "num_tokens": 13816716.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 0.6717162574641407, |
| "epoch": 0.672, |
| "grad_norm": 42.5, |
| "learning_rate": 1.8491111111111112e-05, |
| "loss": 10.9238, |
| "mean_token_accuracy": 0.8044366929680109, |
| "num_tokens": 13895997.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 0.6257681073620915, |
| "epoch": 0.676, |
| "grad_norm": 41.75, |
| "learning_rate": 1.846888888888889e-05, |
| "loss": 9.9056, |
| "mean_token_accuracy": 0.8205471843481064, |
| "num_tokens": 13988168.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 0.6243995727039874, |
| "epoch": 0.68, |
| "grad_norm": 45.5, |
| "learning_rate": 1.8446666666666667e-05, |
| "loss": 10.0775, |
| "mean_token_accuracy": 0.8218194592744112, |
| "num_tokens": 14074579.0, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_biology_entropy": 1.3095218172669412, |
| "eval_biology_loss": 1.3988749980926514, |
| "eval_biology_mean_token_accuracy": 0.6642519612908363, |
| "eval_biology_num_tokens": 14074579.0, |
| "eval_biology_runtime": 35.376, |
| "eval_biology_samples_per_second": 14.134, |
| "eval_biology_steps_per_second": 14.134, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_chemistry_entropy": 0.810583723127842, |
| "eval_chemistry_loss": 0.8362264633178711, |
| "eval_chemistry_mean_token_accuracy": 0.7733853607773781, |
| "eval_chemistry_num_tokens": 14074579.0, |
| "eval_chemistry_runtime": 39.7857, |
| "eval_chemistry_samples_per_second": 12.567, |
| "eval_chemistry_steps_per_second": 12.567, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_math_entropy": 0.7038493918180466, |
| "eval_math_loss": 0.8700717687606812, |
| "eval_math_mean_token_accuracy": 0.7738546322584152, |
| "eval_math_num_tokens": 14074579.0, |
| "eval_math_runtime": 40.5553, |
| "eval_math_samples_per_second": 12.329, |
| "eval_math_steps_per_second": 12.329, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_physics_entropy": 0.6500247009396553, |
| "eval_physics_loss": 0.6439645290374756, |
| "eval_physics_mean_token_accuracy": 0.8147145962715149, |
| "eval_physics_num_tokens": 14074579.0, |
| "eval_physics_runtime": 45.1157, |
| "eval_physics_samples_per_second": 11.083, |
| "eval_physics_steps_per_second": 11.083, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.701755482237786, |
| "epoch": 0.684, |
| "grad_norm": 38.0, |
| "learning_rate": 1.842444444444445e-05, |
| "loss": 11.2097, |
| "mean_token_accuracy": 0.8015010356903076, |
| "num_tokens": 14153649.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 0.6312699088826775, |
| "epoch": 0.688, |
| "grad_norm": 41.5, |
| "learning_rate": 1.8402222222222223e-05, |
| "loss": 10.0591, |
| "mean_token_accuracy": 0.8177381068468094, |
| "num_tokens": 14234888.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 0.6341699136421084, |
| "epoch": 0.692, |
| "grad_norm": 49.75, |
| "learning_rate": 1.8380000000000004e-05, |
| "loss": 10.2054, |
| "mean_token_accuracy": 0.8159505747258663, |
| "num_tokens": 14323183.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 0.6394278825260699, |
| "epoch": 0.696, |
| "grad_norm": 44.0, |
| "learning_rate": 1.8357777777777778e-05, |
| "loss": 10.2597, |
| "mean_token_accuracy": 0.8152242347598075, |
| "num_tokens": 14411150.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 0.6502743780612945, |
| "epoch": 0.7, |
| "grad_norm": 38.0, |
| "learning_rate": 1.833555555555556e-05, |
| "loss": 10.4132, |
| "mean_token_accuracy": 0.8118325512856245, |
| "num_tokens": 14490628.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.6663031128235162, |
| "epoch": 0.704, |
| "grad_norm": 45.0, |
| "learning_rate": 1.8313333333333333e-05, |
| "loss": 10.7733, |
| "mean_token_accuracy": 0.8083227630704641, |
| "num_tokens": 14567908.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 0.6487898311577738, |
| "epoch": 0.708, |
| "grad_norm": 40.0, |
| "learning_rate": 1.8291111111111114e-05, |
| "loss": 10.2458, |
| "mean_token_accuracy": 0.81355558373034, |
| "num_tokens": 14647291.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 0.6143384758383036, |
| "epoch": 0.712, |
| "grad_norm": 42.75, |
| "learning_rate": 1.8268888888888888e-05, |
| "loss": 9.8792, |
| "mean_token_accuracy": 0.8224807776510715, |
| "num_tokens": 14728975.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 0.6461778385564685, |
| "epoch": 0.716, |
| "grad_norm": 42.5, |
| "learning_rate": 1.824666666666667e-05, |
| "loss": 10.16, |
| "mean_token_accuracy": 0.8192640010267496, |
| "num_tokens": 14804586.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 0.6274462300352752, |
| "epoch": 0.72, |
| "grad_norm": 43.5, |
| "learning_rate": 1.8224444444444447e-05, |
| "loss": 10.2187, |
| "mean_token_accuracy": 0.8162837028503418, |
| "num_tokens": 14882927.0, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_biology_entropy": 1.26099048101902, |
| "eval_biology_loss": 1.4029406309127808, |
| "eval_biology_mean_token_accuracy": 0.6639119000434875, |
| "eval_biology_num_tokens": 14882927.0, |
| "eval_biology_runtime": 35.2293, |
| "eval_biology_samples_per_second": 14.193, |
| "eval_biology_steps_per_second": 14.193, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_chemistry_entropy": 0.793392687290907, |
| "eval_chemistry_loss": 0.832188606262207, |
| "eval_chemistry_mean_token_accuracy": 0.7744238600730896, |
| "eval_chemistry_num_tokens": 14882927.0, |
| "eval_chemistry_runtime": 39.6195, |
| "eval_chemistry_samples_per_second": 12.62, |
| "eval_chemistry_steps_per_second": 12.62, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_math_entropy": 0.6914696083068848, |
| "eval_math_loss": 0.8720027804374695, |
| "eval_math_mean_token_accuracy": 0.7736118195652961, |
| "eval_math_num_tokens": 14882927.0, |
| "eval_math_runtime": 40.5243, |
| "eval_math_samples_per_second": 12.338, |
| "eval_math_steps_per_second": 12.338, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_physics_entropy": 0.6349251216948032, |
| "eval_physics_loss": 0.6378234624862671, |
| "eval_physics_mean_token_accuracy": 0.8165309005975723, |
| "eval_physics_num_tokens": 14882927.0, |
| "eval_physics_runtime": 45.1781, |
| "eval_physics_samples_per_second": 11.067, |
| "eval_physics_steps_per_second": 11.067, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.6608743364922702, |
| "epoch": 0.724, |
| "grad_norm": 44.5, |
| "learning_rate": 1.8202222222222225e-05, |
| "loss": 10.4493, |
| "mean_token_accuracy": 0.8107382688671351, |
| "num_tokens": 14966717.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 0.5937761082313955, |
| "epoch": 0.728, |
| "grad_norm": 43.25, |
| "learning_rate": 1.8180000000000002e-05, |
| "loss": 9.6358, |
| "mean_token_accuracy": 0.8237139344215393, |
| "num_tokens": 15052770.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 0.6625786048360169, |
| "epoch": 0.732, |
| "grad_norm": 37.0, |
| "learning_rate": 1.815777777777778e-05, |
| "loss": 10.5736, |
| "mean_token_accuracy": 0.8131286226212978, |
| "num_tokens": 15135882.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 0.6253975971601904, |
| "epoch": 0.736, |
| "grad_norm": 49.5, |
| "learning_rate": 1.8135555555555557e-05, |
| "loss": 9.9433, |
| "mean_token_accuracy": 0.8202268972992897, |
| "num_tokens": 15217342.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 0.6260659927502275, |
| "epoch": 0.74, |
| "grad_norm": 45.75, |
| "learning_rate": 1.8113333333333335e-05, |
| "loss": 10.0495, |
| "mean_token_accuracy": 0.819375942274928, |
| "num_tokens": 15303623.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 0.6029338354244829, |
| "epoch": 0.744, |
| "grad_norm": 46.75, |
| "learning_rate": 1.8091111111111113e-05, |
| "loss": 9.5649, |
| "mean_token_accuracy": 0.8268326785415411, |
| "num_tokens": 15385161.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 0.6492635687813163, |
| "epoch": 0.748, |
| "grad_norm": 47.0, |
| "learning_rate": 1.806888888888889e-05, |
| "loss": 10.568, |
| "mean_token_accuracy": 0.810694944486022, |
| "num_tokens": 15466126.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 0.5932938390411436, |
| "epoch": 0.752, |
| "grad_norm": 43.25, |
| "learning_rate": 1.8046666666666668e-05, |
| "loss": 9.4157, |
| "mean_token_accuracy": 0.8285971570760011, |
| "num_tokens": 15547710.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 0.6472898460924625, |
| "epoch": 0.756, |
| "grad_norm": 47.75, |
| "learning_rate": 1.8024444444444445e-05, |
| "loss": 10.2805, |
| "mean_token_accuracy": 0.8147294465452433, |
| "num_tokens": 15625904.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 0.6560673840343952, |
| "epoch": 0.76, |
| "grad_norm": 43.75, |
| "learning_rate": 1.8002222222222223e-05, |
| "loss": 10.5391, |
| "mean_token_accuracy": 0.8101910080760717, |
| "num_tokens": 15704494.0, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_biology_entropy": 1.3165188397169114, |
| "eval_biology_loss": 1.4028364419937134, |
| "eval_biology_mean_token_accuracy": 0.6636078572869301, |
| "eval_biology_num_tokens": 15704494.0, |
| "eval_biology_runtime": 35.6648, |
| "eval_biology_samples_per_second": 14.019, |
| "eval_biology_steps_per_second": 14.019, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_chemistry_entropy": 0.8100777663588524, |
| "eval_chemistry_loss": 0.8284242749214172, |
| "eval_chemistry_mean_token_accuracy": 0.7751321754455567, |
| "eval_chemistry_num_tokens": 15704494.0, |
| "eval_chemistry_runtime": 39.604, |
| "eval_chemistry_samples_per_second": 12.625, |
| "eval_chemistry_steps_per_second": 12.625, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_math_entropy": 0.7177843990921974, |
| "eval_math_loss": 0.8692219853401184, |
| "eval_math_mean_token_accuracy": 0.7739469853639602, |
| "eval_math_num_tokens": 15704494.0, |
| "eval_math_runtime": 40.511, |
| "eval_math_samples_per_second": 12.342, |
| "eval_math_steps_per_second": 12.342, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_physics_entropy": 0.6514912424087524, |
| "eval_physics_loss": 0.6343158483505249, |
| "eval_physics_mean_token_accuracy": 0.8171744772791862, |
| "eval_physics_num_tokens": 15704494.0, |
| "eval_physics_runtime": 45.1095, |
| "eval_physics_samples_per_second": 11.084, |
| "eval_physics_steps_per_second": 11.084, |
| "step": 1900 |
| }, |
| { |
| "entropy": 0.6272192076779902, |
| "epoch": 0.764, |
| "grad_norm": 38.25, |
| "learning_rate": 1.798e-05, |
| "loss": 9.9781, |
| "mean_token_accuracy": 0.8175393354147673, |
| "num_tokens": 15792219.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 0.619711946696043, |
| "epoch": 0.768, |
| "grad_norm": 39.25, |
| "learning_rate": 1.7957777777777778e-05, |
| "loss": 10.014, |
| "mean_token_accuracy": 0.8173364765942097, |
| "num_tokens": 15877177.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 0.6192873228341341, |
| "epoch": 0.772, |
| "grad_norm": 38.0, |
| "learning_rate": 1.7935555555555556e-05, |
| "loss": 9.8355, |
| "mean_token_accuracy": 0.8235324405133724, |
| "num_tokens": 15965749.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 0.6311636022292078, |
| "epoch": 0.776, |
| "grad_norm": 39.0, |
| "learning_rate": 1.7913333333333337e-05, |
| "loss": 10.0725, |
| "mean_token_accuracy": 0.8187215372920036, |
| "num_tokens": 16050530.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 0.6458089170977473, |
| "epoch": 0.78, |
| "grad_norm": 40.25, |
| "learning_rate": 1.789111111111111e-05, |
| "loss": 10.399, |
| "mean_token_accuracy": 0.8167071305215359, |
| "num_tokens": 16136804.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 0.6231075780466199, |
| "epoch": 0.784, |
| "grad_norm": 43.25, |
| "learning_rate": 1.7868888888888892e-05, |
| "loss": 9.9612, |
| "mean_token_accuracy": 0.8209680158644914, |
| "num_tokens": 16219640.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 0.6302494045346976, |
| "epoch": 0.788, |
| "grad_norm": 39.0, |
| "learning_rate": 1.7846666666666666e-05, |
| "loss": 9.9731, |
| "mean_token_accuracy": 0.8196312204003334, |
| "num_tokens": 16299595.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 0.6404457478784025, |
| "epoch": 0.792, |
| "grad_norm": 51.5, |
| "learning_rate": 1.7824444444444447e-05, |
| "loss": 10.3109, |
| "mean_token_accuracy": 0.8141773957759142, |
| "num_tokens": 16378820.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 0.644137370865792, |
| "epoch": 0.796, |
| "grad_norm": 44.25, |
| "learning_rate": 1.780222222222222e-05, |
| "loss": 10.3859, |
| "mean_token_accuracy": 0.8138818342238665, |
| "num_tokens": 16464611.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 0.6414632762782275, |
| "epoch": 0.8, |
| "grad_norm": 35.0, |
| "learning_rate": 1.7780000000000003e-05, |
| "loss": 10.2348, |
| "mean_token_accuracy": 0.8169484097510576, |
| "num_tokens": 16548261.0, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_biology_entropy": 1.310195390045643, |
| "eval_biology_loss": 1.3905400037765503, |
| "eval_biology_mean_token_accuracy": 0.6651642812490464, |
| "eval_biology_num_tokens": 16548261.0, |
| "eval_biology_runtime": 35.3115, |
| "eval_biology_samples_per_second": 14.16, |
| "eval_biology_steps_per_second": 14.16, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_chemistry_entropy": 0.7988228353559971, |
| "eval_chemistry_loss": 0.8260599374771118, |
| "eval_chemistry_mean_token_accuracy": 0.7754636185765267, |
| "eval_chemistry_num_tokens": 16548261.0, |
| "eval_chemistry_runtime": 39.4167, |
| "eval_chemistry_samples_per_second": 12.685, |
| "eval_chemistry_steps_per_second": 12.685, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_math_entropy": 0.6841731403172017, |
| "eval_math_loss": 0.87116539478302, |
| "eval_math_mean_token_accuracy": 0.7759169373512268, |
| "eval_math_num_tokens": 16548261.0, |
| "eval_math_runtime": 40.3625, |
| "eval_math_samples_per_second": 12.388, |
| "eval_math_steps_per_second": 12.388, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_physics_entropy": 0.6220660482347011, |
| "eval_physics_loss": 0.6307912468910217, |
| "eval_physics_mean_token_accuracy": 0.818623253762722, |
| "eval_physics_num_tokens": 16548261.0, |
| "eval_physics_runtime": 45.0164, |
| "eval_physics_samples_per_second": 11.107, |
| "eval_physics_steps_per_second": 11.107, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 10000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 1.1096331558472863e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
