| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.4, |
| "eval_steps": 100, |
| "global_step": 6000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.3589675037190318, |
| "epoch": 0.004, |
| "grad_norm": 221.0, |
| "learning_rate": 1.8e-07, |
| "loss": 14.235, |
| "mean_token_accuracy": 0.8023731399327516, |
| "num_tokens": 89176.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.381451623653993, |
| "epoch": 0.008, |
| "grad_norm": 251.0, |
| "learning_rate": 3.8e-07, |
| "loss": 16.438, |
| "mean_token_accuracy": 0.7818928115069866, |
| "num_tokens": 173886.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.36998924349900336, |
| "epoch": 0.012, |
| "grad_norm": 284.0, |
| "learning_rate": 5.800000000000001e-07, |
| "loss": 15.3069, |
| "mean_token_accuracy": 0.7961655277758837, |
| "num_tokens": 258970.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.3889644297771156, |
| "epoch": 0.016, |
| "grad_norm": 296.0, |
| "learning_rate": 7.8e-07, |
| "loss": 15.6587, |
| "mean_token_accuracy": 0.7874974697828293, |
| "num_tokens": 338352.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.3830348197836429, |
| "epoch": 0.02, |
| "grad_norm": 330.0, |
| "learning_rate": 9.800000000000001e-07, |
| "loss": 15.0754, |
| "mean_token_accuracy": 0.7973605334758759, |
| "num_tokens": 424243.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.40132593517191706, |
| "epoch": 0.024, |
| "grad_norm": 284.0, |
| "learning_rate": 1.1800000000000001e-06, |
| "loss": 15.9374, |
| "mean_token_accuracy": 0.7853362146764994, |
| "num_tokens": 505613.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.41173397554084656, |
| "epoch": 0.028, |
| "grad_norm": 201.0, |
| "learning_rate": 1.3800000000000001e-06, |
| "loss": 15.1473, |
| "mean_token_accuracy": 0.7896888509392739, |
| "num_tokens": 584157.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.4223371436353773, |
| "epoch": 0.032, |
| "grad_norm": 164.0, |
| "learning_rate": 1.5800000000000001e-06, |
| "loss": 13.7069, |
| "mean_token_accuracy": 0.8018626874312759, |
| "num_tokens": 671193.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.4982604907825589, |
| "epoch": 0.036, |
| "grad_norm": 240.0, |
| "learning_rate": 1.7800000000000001e-06, |
| "loss": 14.6572, |
| "mean_token_accuracy": 0.7824514407664538, |
| "num_tokens": 753947.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.4913600580766797, |
| "epoch": 0.04, |
| "grad_norm": 155.0, |
| "learning_rate": 1.98e-06, |
| "loss": 13.0149, |
| "mean_token_accuracy": 0.8003234412521124, |
| "num_tokens": 835868.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_chemistry_entropy": 0.41473443768918516, |
| "eval_chemistry_loss": 0.7713431119918823, |
| "eval_chemistry_mean_token_accuracy": 0.8103395719528198, |
| "eval_chemistry_num_tokens": 835868.0, |
| "eval_chemistry_runtime": 53.7203, |
| "eval_chemistry_samples_per_second": 9.307, |
| "eval_chemistry_steps_per_second": 9.307, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_physics_entropy": 0.5291771245449781, |
| "eval_physics_loss": 0.8209348917007446, |
| "eval_physics_mean_token_accuracy": 0.7944456633925437, |
| "eval_physics_num_tokens": 835868.0, |
| "eval_physics_runtime": 62.4292, |
| "eval_physics_samples_per_second": 8.009, |
| "eval_physics_steps_per_second": 8.009, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.5052730706520379, |
| "epoch": 0.044, |
| "grad_norm": 132.0, |
| "learning_rate": 2.1800000000000003e-06, |
| "loss": 11.9999, |
| "mean_token_accuracy": 0.807476469874382, |
| "num_tokens": 917534.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.5510593980550766, |
| "epoch": 0.048, |
| "grad_norm": 100.5, |
| "learning_rate": 2.38e-06, |
| "loss": 11.8438, |
| "mean_token_accuracy": 0.8063667319715023, |
| "num_tokens": 1001008.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.59730707956478, |
| "epoch": 0.052, |
| "grad_norm": 87.5, |
| "learning_rate": 2.5800000000000003e-06, |
| "loss": 11.8941, |
| "mean_token_accuracy": 0.8023553561419249, |
| "num_tokens": 1085098.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.6581894762814045, |
| "epoch": 0.056, |
| "grad_norm": 102.0, |
| "learning_rate": 2.7800000000000005e-06, |
| "loss": 12.6245, |
| "mean_token_accuracy": 0.7945734079927206, |
| "num_tokens": 1166615.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.6519844191148877, |
| "epoch": 0.06, |
| "grad_norm": 70.5, |
| "learning_rate": 2.9800000000000003e-06, |
| "loss": 11.5194, |
| "mean_token_accuracy": 0.8026637583971024, |
| "num_tokens": 1248387.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.7085968372412026, |
| "epoch": 0.064, |
| "grad_norm": 72.0, |
| "learning_rate": 3.1800000000000005e-06, |
| "loss": 12.4073, |
| "mean_token_accuracy": 0.7906260795891284, |
| "num_tokens": 1331208.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.6624301395379006, |
| "epoch": 0.068, |
| "grad_norm": 66.5, |
| "learning_rate": 3.3800000000000007e-06, |
| "loss": 11.3744, |
| "mean_token_accuracy": 0.8067036394029856, |
| "num_tokens": 1416841.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.664617495983839, |
| "epoch": 0.072, |
| "grad_norm": 70.5, |
| "learning_rate": 3.58e-06, |
| "loss": 11.3264, |
| "mean_token_accuracy": 0.8068108163774014, |
| "num_tokens": 1499449.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.6721668383106589, |
| "epoch": 0.076, |
| "grad_norm": 70.5, |
| "learning_rate": 3.7800000000000002e-06, |
| "loss": 11.2874, |
| "mean_token_accuracy": 0.8029039859771728, |
| "num_tokens": 1585982.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.6800463449209928, |
| "epoch": 0.08, |
| "grad_norm": 58.5, |
| "learning_rate": 3.980000000000001e-06, |
| "loss": 11.4959, |
| "mean_token_accuracy": 0.8001787267625332, |
| "num_tokens": 1667532.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_chemistry_entropy": 0.579608644425869, |
| "eval_chemistry_loss": 0.6572756171226501, |
| "eval_chemistry_mean_token_accuracy": 0.8160659775733948, |
| "eval_chemistry_num_tokens": 1667532.0, |
| "eval_chemistry_runtime": 53.9736, |
| "eval_chemistry_samples_per_second": 9.264, |
| "eval_chemistry_steps_per_second": 9.264, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_physics_entropy": 0.6811966061294079, |
| "eval_physics_loss": 0.714818000793457, |
| "eval_physics_mean_token_accuracy": 0.8037424722313881, |
| "eval_physics_num_tokens": 1667532.0, |
| "eval_physics_runtime": 62.6745, |
| "eval_physics_samples_per_second": 7.978, |
| "eval_physics_steps_per_second": 7.978, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.6441303874365986, |
| "epoch": 0.084, |
| "grad_norm": 65.5, |
| "learning_rate": 4.18e-06, |
| "loss": 10.9679, |
| "mean_token_accuracy": 0.8105842903256416, |
| "num_tokens": 1750813.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.7001293174922466, |
| "epoch": 0.088, |
| "grad_norm": 63.5, |
| "learning_rate": 4.38e-06, |
| "loss": 11.3739, |
| "mean_token_accuracy": 0.8039855100214481, |
| "num_tokens": 1835489.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.7212686208076775, |
| "epoch": 0.092, |
| "grad_norm": 68.5, |
| "learning_rate": 4.58e-06, |
| "loss": 11.9056, |
| "mean_token_accuracy": 0.7951413784176111, |
| "num_tokens": 1915115.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.6619318895973265, |
| "epoch": 0.096, |
| "grad_norm": 66.5, |
| "learning_rate": 4.78e-06, |
| "loss": 10.9428, |
| "mean_token_accuracy": 0.8108693141490221, |
| "num_tokens": 2007176.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.6880421325564384, |
| "epoch": 0.1, |
| "grad_norm": 55.5, |
| "learning_rate": 4.980000000000001e-06, |
| "loss": 11.3231, |
| "mean_token_accuracy": 0.8026650555431842, |
| "num_tokens": 2088696.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.7066576741635799, |
| "epoch": 0.104, |
| "grad_norm": 58.25, |
| "learning_rate": 5.18e-06, |
| "loss": 11.6232, |
| "mean_token_accuracy": 0.799198641628027, |
| "num_tokens": 2171335.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.6949395652860403, |
| "epoch": 0.108, |
| "grad_norm": 69.5, |
| "learning_rate": 5.380000000000001e-06, |
| "loss": 11.2549, |
| "mean_token_accuracy": 0.8055713165551424, |
| "num_tokens": 2254168.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.666729858610779, |
| "epoch": 0.112, |
| "grad_norm": 67.0, |
| "learning_rate": 5.580000000000001e-06, |
| "loss": 10.8193, |
| "mean_token_accuracy": 0.8086711473762989, |
| "num_tokens": 2342259.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.6924487132579088, |
| "epoch": 0.116, |
| "grad_norm": 60.5, |
| "learning_rate": 5.78e-06, |
| "loss": 11.1656, |
| "mean_token_accuracy": 0.8066085658967495, |
| "num_tokens": 2426289.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.7209857527166605, |
| "epoch": 0.12, |
| "grad_norm": 53.75, |
| "learning_rate": 5.98e-06, |
| "loss": 11.7716, |
| "mean_token_accuracy": 0.7946148321032525, |
| "num_tokens": 2504279.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_chemistry_entropy": 0.6136138401329517, |
| "eval_chemistry_loss": 0.6401469707489014, |
| "eval_chemistry_mean_token_accuracy": 0.8167599263191223, |
| "eval_chemistry_num_tokens": 2504279.0, |
| "eval_chemistry_runtime": 53.6939, |
| "eval_chemistry_samples_per_second": 9.312, |
| "eval_chemistry_steps_per_second": 9.312, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_physics_entropy": 0.678692765057087, |
| "eval_physics_loss": 0.6855186820030212, |
| "eval_physics_mean_token_accuracy": 0.8083885474801064, |
| "eval_physics_num_tokens": 2504279.0, |
| "eval_physics_runtime": 62.4413, |
| "eval_physics_samples_per_second": 8.008, |
| "eval_physics_steps_per_second": 8.008, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.7016886103898287, |
| "epoch": 0.124, |
| "grad_norm": 51.0, |
| "learning_rate": 6.18e-06, |
| "loss": 11.5109, |
| "mean_token_accuracy": 0.79740143828094, |
| "num_tokens": 2583599.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.6659886735491455, |
| "epoch": 0.128, |
| "grad_norm": 50.5, |
| "learning_rate": 6.380000000000001e-06, |
| "loss": 10.6687, |
| "mean_token_accuracy": 0.8114107441157102, |
| "num_tokens": 2663987.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.6984131418168544, |
| "epoch": 0.132, |
| "grad_norm": 55.5, |
| "learning_rate": 6.5800000000000005e-06, |
| "loss": 11.5084, |
| "mean_token_accuracy": 0.8018826052546502, |
| "num_tokens": 2743933.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.685006461199373, |
| "epoch": 0.136, |
| "grad_norm": 43.25, |
| "learning_rate": 6.780000000000001e-06, |
| "loss": 11.0885, |
| "mean_token_accuracy": 0.8083073671907186, |
| "num_tokens": 2829720.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.6919135926291347, |
| "epoch": 0.14, |
| "grad_norm": 44.25, |
| "learning_rate": 6.98e-06, |
| "loss": 11.1629, |
| "mean_token_accuracy": 0.8035723548382521, |
| "num_tokens": 2915814.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.6693393810652196, |
| "epoch": 0.144, |
| "grad_norm": 68.5, |
| "learning_rate": 7.180000000000001e-06, |
| "loss": 10.8935, |
| "mean_token_accuracy": 0.8098476737737655, |
| "num_tokens": 2997824.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.6817218182608485, |
| "epoch": 0.148, |
| "grad_norm": 55.0, |
| "learning_rate": 7.3800000000000005e-06, |
| "loss": 10.9932, |
| "mean_token_accuracy": 0.8062656305730342, |
| "num_tokens": 3076422.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.6472045814618468, |
| "epoch": 0.152, |
| "grad_norm": 48.5, |
| "learning_rate": 7.58e-06, |
| "loss": 10.5274, |
| "mean_token_accuracy": 0.8134200550615788, |
| "num_tokens": 3159946.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.639185450039804, |
| "epoch": 0.156, |
| "grad_norm": 54.25, |
| "learning_rate": 7.78e-06, |
| "loss": 10.3706, |
| "mean_token_accuracy": 0.8159802399575711, |
| "num_tokens": 3247218.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.6741150500252843, |
| "epoch": 0.16, |
| "grad_norm": 53.25, |
| "learning_rate": 7.980000000000002e-06, |
| "loss": 10.9071, |
| "mean_token_accuracy": 0.8088992539793253, |
| "num_tokens": 3330597.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_chemistry_entropy": 0.6244144983887673, |
| "eval_chemistry_loss": 0.6363974809646606, |
| "eval_chemistry_mean_token_accuracy": 0.8181359567642212, |
| "eval_chemistry_num_tokens": 3330597.0, |
| "eval_chemistry_runtime": 53.6338, |
| "eval_chemistry_samples_per_second": 9.322, |
| "eval_chemistry_steps_per_second": 9.322, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_physics_entropy": 0.6705876287817955, |
| "eval_physics_loss": 0.6704522371292114, |
| "eval_physics_mean_token_accuracy": 0.8111195236444473, |
| "eval_physics_num_tokens": 3330597.0, |
| "eval_physics_runtime": 62.3611, |
| "eval_physics_samples_per_second": 8.018, |
| "eval_physics_steps_per_second": 8.018, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.6919050188735127, |
| "epoch": 0.164, |
| "grad_norm": 57.25, |
| "learning_rate": 8.18e-06, |
| "loss": 11.1447, |
| "mean_token_accuracy": 0.8047709062695503, |
| "num_tokens": 3414445.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.6699288227595389, |
| "epoch": 0.168, |
| "grad_norm": 59.75, |
| "learning_rate": 8.380000000000001e-06, |
| "loss": 10.7791, |
| "mean_token_accuracy": 0.8070078935474158, |
| "num_tokens": 3496104.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.6792626342736184, |
| "epoch": 0.172, |
| "grad_norm": 48.75, |
| "learning_rate": 8.580000000000001e-06, |
| "loss": 11.0757, |
| "mean_token_accuracy": 0.8060608543455601, |
| "num_tokens": 3576979.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.6533824939280748, |
| "epoch": 0.176, |
| "grad_norm": 61.0, |
| "learning_rate": 8.78e-06, |
| "loss": 10.5681, |
| "mean_token_accuracy": 0.8110670737922192, |
| "num_tokens": 3658264.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.6711471493355929, |
| "epoch": 0.18, |
| "grad_norm": 57.25, |
| "learning_rate": 8.98e-06, |
| "loss": 10.9005, |
| "mean_token_accuracy": 0.8076804723590613, |
| "num_tokens": 3739142.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.6721100191585719, |
| "epoch": 0.184, |
| "grad_norm": 55.0, |
| "learning_rate": 9.180000000000002e-06, |
| "loss": 10.792, |
| "mean_token_accuracy": 0.8070170730352402, |
| "num_tokens": 3821352.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.6371375021524728, |
| "epoch": 0.188, |
| "grad_norm": 45.75, |
| "learning_rate": 9.38e-06, |
| "loss": 10.3376, |
| "mean_token_accuracy": 0.8134377617388964, |
| "num_tokens": 3905291.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.6436822958290577, |
| "epoch": 0.192, |
| "grad_norm": 45.75, |
| "learning_rate": 9.58e-06, |
| "loss": 10.4275, |
| "mean_token_accuracy": 0.8145703230053186, |
| "num_tokens": 3995568.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.6615747599862516, |
| "epoch": 0.196, |
| "grad_norm": 55.25, |
| "learning_rate": 9.780000000000001e-06, |
| "loss": 10.75, |
| "mean_token_accuracy": 0.8106145299971104, |
| "num_tokens": 4075670.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.6414908402599394, |
| "epoch": 0.2, |
| "grad_norm": 55.0, |
| "learning_rate": 9.980000000000001e-06, |
| "loss": 10.318, |
| "mean_token_accuracy": 0.8157790113240481, |
| "num_tokens": 4160918.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_chemistry_entropy": 0.6180844354629517, |
| "eval_chemistry_loss": 0.6358755230903625, |
| "eval_chemistry_mean_token_accuracy": 0.8190241982936859, |
| "eval_chemistry_num_tokens": 4160918.0, |
| "eval_chemistry_runtime": 53.6, |
| "eval_chemistry_samples_per_second": 9.328, |
| "eval_chemistry_steps_per_second": 9.328, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_physics_entropy": 0.6517913154959679, |
| "eval_physics_loss": 0.6597976088523865, |
| "eval_physics_mean_token_accuracy": 0.8130922448635102, |
| "eval_physics_num_tokens": 4160918.0, |
| "eval_physics_runtime": 62.5405, |
| "eval_physics_samples_per_second": 7.995, |
| "eval_physics_steps_per_second": 7.995, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.6417077989317477, |
| "epoch": 0.204, |
| "grad_norm": 48.75, |
| "learning_rate": 1.018e-05, |
| "loss": 10.4263, |
| "mean_token_accuracy": 0.8166976355016231, |
| "num_tokens": 4238810.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.635231535602361, |
| "epoch": 0.208, |
| "grad_norm": 48.75, |
| "learning_rate": 1.038e-05, |
| "loss": 10.327, |
| "mean_token_accuracy": 0.8165579732507467, |
| "num_tokens": 4321436.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.6600574821233749, |
| "epoch": 0.212, |
| "grad_norm": 49.5, |
| "learning_rate": 1.0580000000000002e-05, |
| "loss": 10.4772, |
| "mean_token_accuracy": 0.811732816696167, |
| "num_tokens": 4401710.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.6544907880946994, |
| "epoch": 0.216, |
| "grad_norm": 46.75, |
| "learning_rate": 1.0780000000000002e-05, |
| "loss": 10.7566, |
| "mean_token_accuracy": 0.808320876955986, |
| "num_tokens": 4482225.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.6429057026281952, |
| "epoch": 0.22, |
| "grad_norm": 51.25, |
| "learning_rate": 1.0980000000000002e-05, |
| "loss": 10.4272, |
| "mean_token_accuracy": 0.8134562011808157, |
| "num_tokens": 4564662.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.6186996471136809, |
| "epoch": 0.224, |
| "grad_norm": 42.0, |
| "learning_rate": 1.1180000000000001e-05, |
| "loss": 9.9666, |
| "mean_token_accuracy": 0.8213985275477171, |
| "num_tokens": 4648491.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.6025784744881093, |
| "epoch": 0.228, |
| "grad_norm": 40.75, |
| "learning_rate": 1.138e-05, |
| "loss": 9.8638, |
| "mean_token_accuracy": 0.8230083137750626, |
| "num_tokens": 4731596.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.6584511337801814, |
| "epoch": 0.232, |
| "grad_norm": 45.0, |
| "learning_rate": 1.1580000000000001e-05, |
| "loss": 10.6688, |
| "mean_token_accuracy": 0.8104485847055912, |
| "num_tokens": 4813449.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.6477856112644076, |
| "epoch": 0.236, |
| "grad_norm": 40.25, |
| "learning_rate": 1.178e-05, |
| "loss": 10.3036, |
| "mean_token_accuracy": 0.8149273872375489, |
| "num_tokens": 4899144.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.632176025211811, |
| "epoch": 0.24, |
| "grad_norm": 44.5, |
| "learning_rate": 1.198e-05, |
| "loss": 10.4072, |
| "mean_token_accuracy": 0.8141517870128154, |
| "num_tokens": 4986175.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_chemistry_entropy": 0.6246057401299476, |
| "eval_chemistry_loss": 0.6355127096176147, |
| "eval_chemistry_mean_token_accuracy": 0.8170186321735382, |
| "eval_chemistry_num_tokens": 4986175.0, |
| "eval_chemistry_runtime": 53.7353, |
| "eval_chemistry_samples_per_second": 9.305, |
| "eval_chemistry_steps_per_second": 9.305, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_physics_entropy": 0.6429958860874176, |
| "eval_physics_loss": 0.6528828740119934, |
| "eval_physics_mean_token_accuracy": 0.8143444744944572, |
| "eval_physics_num_tokens": 4986175.0, |
| "eval_physics_runtime": 62.4695, |
| "eval_physics_samples_per_second": 8.004, |
| "eval_physics_steps_per_second": 8.004, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.6520758749917149, |
| "epoch": 0.244, |
| "grad_norm": 50.0, |
| "learning_rate": 1.218e-05, |
| "loss": 10.5332, |
| "mean_token_accuracy": 0.8124375600367785, |
| "num_tokens": 5071994.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.6255051350221038, |
| "epoch": 0.248, |
| "grad_norm": 43.5, |
| "learning_rate": 1.2380000000000002e-05, |
| "loss": 10.0529, |
| "mean_token_accuracy": 0.8187242690473795, |
| "num_tokens": 5164741.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.6554224069230259, |
| "epoch": 0.252, |
| "grad_norm": 47.5, |
| "learning_rate": 1.2580000000000002e-05, |
| "loss": 10.7383, |
| "mean_token_accuracy": 0.8093429666012526, |
| "num_tokens": 5245878.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.635463903658092, |
| "epoch": 0.256, |
| "grad_norm": 51.0, |
| "learning_rate": 1.2780000000000001e-05, |
| "loss": 10.3241, |
| "mean_token_accuracy": 0.8143212880939246, |
| "num_tokens": 5329320.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.6407582541927695, |
| "epoch": 0.26, |
| "grad_norm": 44.75, |
| "learning_rate": 1.2980000000000001e-05, |
| "loss": 10.3061, |
| "mean_token_accuracy": 0.8153956741094589, |
| "num_tokens": 5412557.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.6218360926955938, |
| "epoch": 0.264, |
| "grad_norm": 55.25, |
| "learning_rate": 1.3180000000000001e-05, |
| "loss": 10.1715, |
| "mean_token_accuracy": 0.8187983844429254, |
| "num_tokens": 5497259.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.6525244776159524, |
| "epoch": 0.268, |
| "grad_norm": 48.5, |
| "learning_rate": 1.3380000000000002e-05, |
| "loss": 10.5148, |
| "mean_token_accuracy": 0.8133967652916908, |
| "num_tokens": 5576721.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.6617097955197095, |
| "epoch": 0.272, |
| "grad_norm": 50.0, |
| "learning_rate": 1.3580000000000002e-05, |
| "loss": 10.7486, |
| "mean_token_accuracy": 0.8067130610346794, |
| "num_tokens": 5658796.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.6757121763192118, |
| "epoch": 0.276, |
| "grad_norm": 47.25, |
| "learning_rate": 1.378e-05, |
| "loss": 10.8755, |
| "mean_token_accuracy": 0.8065906465053558, |
| "num_tokens": 5737499.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.6453007774427533, |
| "epoch": 0.28, |
| "grad_norm": 62.5, |
| "learning_rate": 1.398e-05, |
| "loss": 10.4792, |
| "mean_token_accuracy": 0.8154859133064747, |
| "num_tokens": 5819027.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_chemistry_entropy": 0.6300962825417519, |
| "eval_chemistry_loss": 0.6389291882514954, |
| "eval_chemistry_mean_token_accuracy": 0.8176450840234757, |
| "eval_chemistry_num_tokens": 5819027.0, |
| "eval_chemistry_runtime": 53.7695, |
| "eval_chemistry_samples_per_second": 9.299, |
| "eval_chemistry_steps_per_second": 9.299, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_physics_entropy": 0.6429837597608566, |
| "eval_physics_loss": 0.6483125686645508, |
| "eval_physics_mean_token_accuracy": 0.8155634801387787, |
| "eval_physics_num_tokens": 5819027.0, |
| "eval_physics_runtime": 62.5294, |
| "eval_physics_samples_per_second": 7.996, |
| "eval_physics_steps_per_second": 7.996, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.6762596594169736, |
| "epoch": 0.284, |
| "grad_norm": 59.0, |
| "learning_rate": 1.418e-05, |
| "loss": 10.8583, |
| "mean_token_accuracy": 0.8072559602558613, |
| "num_tokens": 5898693.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.6340524691157043, |
| "epoch": 0.288, |
| "grad_norm": 47.75, |
| "learning_rate": 1.4380000000000001e-05, |
| "loss": 10.3892, |
| "mean_token_accuracy": 0.8159883081912994, |
| "num_tokens": 5980201.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.6257706139236688, |
| "epoch": 0.292, |
| "grad_norm": 46.25, |
| "learning_rate": 1.4580000000000001e-05, |
| "loss": 10.052, |
| "mean_token_accuracy": 0.8204058665782213, |
| "num_tokens": 6059507.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.6355020292103291, |
| "epoch": 0.296, |
| "grad_norm": 47.0, |
| "learning_rate": 1.478e-05, |
| "loss": 10.3665, |
| "mean_token_accuracy": 0.8142751138657331, |
| "num_tokens": 6139830.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.6532576438970864, |
| "epoch": 0.3, |
| "grad_norm": 47.25, |
| "learning_rate": 1.498e-05, |
| "loss": 10.3728, |
| "mean_token_accuracy": 0.8153154000639915, |
| "num_tokens": 6218134.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.6463365102186799, |
| "epoch": 0.304, |
| "grad_norm": 47.0, |
| "learning_rate": 1.5180000000000002e-05, |
| "loss": 10.4965, |
| "mean_token_accuracy": 0.8147804290056229, |
| "num_tokens": 6298858.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.6870367551222444, |
| "epoch": 0.308, |
| "grad_norm": 55.0, |
| "learning_rate": 1.5380000000000002e-05, |
| "loss": 11.2005, |
| "mean_token_accuracy": 0.8020890522748232, |
| "num_tokens": 6375761.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.6256772884167731, |
| "epoch": 0.312, |
| "grad_norm": 41.75, |
| "learning_rate": 1.5580000000000003e-05, |
| "loss": 10.0914, |
| "mean_token_accuracy": 0.8196329109370708, |
| "num_tokens": 6456502.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.6423514087684452, |
| "epoch": 0.316, |
| "grad_norm": 49.75, |
| "learning_rate": 1.578e-05, |
| "loss": 10.492, |
| "mean_token_accuracy": 0.8146003533154726, |
| "num_tokens": 6537521.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.6631265950389207, |
| "epoch": 0.32, |
| "grad_norm": 43.0, |
| "learning_rate": 1.5980000000000003e-05, |
| "loss": 10.7489, |
| "mean_token_accuracy": 0.8101503010839224, |
| "num_tokens": 6622798.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_chemistry_entropy": 0.6421979127824307, |
| "eval_chemistry_loss": 0.6415462493896484, |
| "eval_chemistry_mean_token_accuracy": 0.817062867641449, |
| "eval_chemistry_num_tokens": 6622798.0, |
| "eval_chemistry_runtime": 53.6883, |
| "eval_chemistry_samples_per_second": 9.313, |
| "eval_chemistry_steps_per_second": 9.313, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_physics_entropy": 0.6440860625505448, |
| "eval_physics_loss": 0.6467884182929993, |
| "eval_physics_mean_token_accuracy": 0.8157004522681236, |
| "eval_physics_num_tokens": 6622798.0, |
| "eval_physics_runtime": 62.4499, |
| "eval_physics_samples_per_second": 8.006, |
| "eval_physics_steps_per_second": 8.006, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.6417643938213586, |
| "epoch": 0.324, |
| "grad_norm": 54.0, |
| "learning_rate": 1.618e-05, |
| "loss": 10.54, |
| "mean_token_accuracy": 0.8144381437450647, |
| "num_tokens": 6699373.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.6635292621329427, |
| "epoch": 0.328, |
| "grad_norm": 43.25, |
| "learning_rate": 1.638e-05, |
| "loss": 10.6337, |
| "mean_token_accuracy": 0.8078649930655957, |
| "num_tokens": 6782985.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.6515420666895807, |
| "epoch": 0.332, |
| "grad_norm": 51.5, |
| "learning_rate": 1.658e-05, |
| "loss": 10.4447, |
| "mean_token_accuracy": 0.8119669426232576, |
| "num_tokens": 6868578.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.6081873361952603, |
| "epoch": 0.336, |
| "grad_norm": 40.0, |
| "learning_rate": 1.6780000000000002e-05, |
| "loss": 9.8522, |
| "mean_token_accuracy": 0.8244299061596394, |
| "num_tokens": 6953611.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.6503613390959799, |
| "epoch": 0.34, |
| "grad_norm": 52.0, |
| "learning_rate": 1.698e-05, |
| "loss": 10.6425, |
| "mean_token_accuracy": 0.8126828409731388, |
| "num_tokens": 7037831.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.611198160611093, |
| "epoch": 0.344, |
| "grad_norm": 56.75, |
| "learning_rate": 1.718e-05, |
| "loss": 9.9189, |
| "mean_token_accuracy": 0.8207242820411921, |
| "num_tokens": 7121949.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.6327245706692338, |
| "epoch": 0.348, |
| "grad_norm": 44.0, |
| "learning_rate": 1.7380000000000003e-05, |
| "loss": 10.2368, |
| "mean_token_accuracy": 0.8166516173630953, |
| "num_tokens": 7206056.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.6341161539778113, |
| "epoch": 0.352, |
| "grad_norm": 51.5, |
| "learning_rate": 1.758e-05, |
| "loss": 10.2941, |
| "mean_token_accuracy": 0.816456102579832, |
| "num_tokens": 7290378.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.6554373924620449, |
| "epoch": 0.356, |
| "grad_norm": 42.5, |
| "learning_rate": 1.7780000000000003e-05, |
| "loss": 10.5667, |
| "mean_token_accuracy": 0.8104542337357998, |
| "num_tokens": 7367952.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.6374449659138918, |
| "epoch": 0.36, |
| "grad_norm": 59.75, |
| "learning_rate": 1.798e-05, |
| "loss": 10.3565, |
| "mean_token_accuracy": 0.816227027028799, |
| "num_tokens": 7452920.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_chemistry_entropy": 0.6640482069849968, |
| "eval_chemistry_loss": 0.6512866020202637, |
| "eval_chemistry_mean_token_accuracy": 0.8145369750261306, |
| "eval_chemistry_num_tokens": 7452920.0, |
| "eval_chemistry_runtime": 53.5846, |
| "eval_chemistry_samples_per_second": 9.331, |
| "eval_chemistry_steps_per_second": 9.331, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_physics_entropy": 0.65689039093256, |
| "eval_physics_loss": 0.64650559425354, |
| "eval_physics_mean_token_accuracy": 0.8153353578448296, |
| "eval_physics_num_tokens": 7452920.0, |
| "eval_physics_runtime": 62.3633, |
| "eval_physics_samples_per_second": 8.018, |
| "eval_physics_steps_per_second": 8.018, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.6258705526590347, |
| "epoch": 0.364, |
| "grad_norm": 43.75, |
| "learning_rate": 1.8180000000000002e-05, |
| "loss": 10.013, |
| "mean_token_accuracy": 0.8192542195320129, |
| "num_tokens": 7535961.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 0.6131137845106422, |
| "epoch": 0.368, |
| "grad_norm": 43.5, |
| "learning_rate": 1.8380000000000004e-05, |
| "loss": 9.9858, |
| "mean_token_accuracy": 0.8190763648599386, |
| "num_tokens": 7621082.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 0.6138401796109975, |
| "epoch": 0.372, |
| "grad_norm": 46.75, |
| "learning_rate": 1.858e-05, |
| "loss": 10.0396, |
| "mean_token_accuracy": 0.8174721483141184, |
| "num_tokens": 7705651.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 0.7146476589143276, |
| "epoch": 0.376, |
| "grad_norm": 46.25, |
| "learning_rate": 1.878e-05, |
| "loss": 11.4452, |
| "mean_token_accuracy": 0.7953129142522812, |
| "num_tokens": 7787036.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 0.6485187427140773, |
| "epoch": 0.38, |
| "grad_norm": 56.5, |
| "learning_rate": 1.898e-05, |
| "loss": 10.5487, |
| "mean_token_accuracy": 0.8087487578392029, |
| "num_tokens": 7869437.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.633660759497434, |
| "epoch": 0.384, |
| "grad_norm": 42.0, |
| "learning_rate": 1.918e-05, |
| "loss": 10.1676, |
| "mean_token_accuracy": 0.8168184392154216, |
| "num_tokens": 7955570.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 0.5985365292057395, |
| "epoch": 0.388, |
| "grad_norm": 38.25, |
| "learning_rate": 1.938e-05, |
| "loss": 9.8157, |
| "mean_token_accuracy": 0.8218576721847057, |
| "num_tokens": 8038818.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 0.6344430455937982, |
| "epoch": 0.392, |
| "grad_norm": 39.75, |
| "learning_rate": 1.9580000000000002e-05, |
| "loss": 10.1821, |
| "mean_token_accuracy": 0.8146390464156866, |
| "num_tokens": 8123527.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 0.6378526957705617, |
| "epoch": 0.396, |
| "grad_norm": 43.75, |
| "learning_rate": 1.978e-05, |
| "loss": 10.2889, |
| "mean_token_accuracy": 0.8144868839532137, |
| "num_tokens": 8206501.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 0.6167035531252623, |
| "epoch": 0.4, |
| "grad_norm": 36.25, |
| "learning_rate": 1.9980000000000002e-05, |
| "loss": 10.0591, |
| "mean_token_accuracy": 0.819990050420165, |
| "num_tokens": 8291049.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_chemistry_entropy": 0.6586475971937179, |
| "eval_chemistry_loss": 0.6543877124786377, |
| "eval_chemistry_mean_token_accuracy": 0.8140276271104813, |
| "eval_chemistry_num_tokens": 8291049.0, |
| "eval_chemistry_runtime": 53.801, |
| "eval_chemistry_samples_per_second": 9.294, |
| "eval_chemistry_steps_per_second": 9.294, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_physics_entropy": 0.645909442961216, |
| "eval_physics_loss": 0.6488538980484009, |
| "eval_physics_mean_token_accuracy": 0.8152267854809762, |
| "eval_physics_num_tokens": 8291049.0, |
| "eval_physics_runtime": 63.4318, |
| "eval_physics_samples_per_second": 7.882, |
| "eval_physics_steps_per_second": 7.882, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.6288712982088327, |
| "epoch": 0.404, |
| "grad_norm": 44.75, |
| "learning_rate": 1.9980000000000002e-05, |
| "loss": 10.1535, |
| "mean_token_accuracy": 0.8175500966608524, |
| "num_tokens": 8373687.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 0.6477080984972418, |
| "epoch": 0.408, |
| "grad_norm": 41.25, |
| "learning_rate": 1.995777777777778e-05, |
| "loss": 10.4444, |
| "mean_token_accuracy": 0.8120142377912998, |
| "num_tokens": 8459795.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 0.6198763550259173, |
| "epoch": 0.412, |
| "grad_norm": 48.25, |
| "learning_rate": 1.9935555555555557e-05, |
| "loss": 10.145, |
| "mean_token_accuracy": 0.8183699958026409, |
| "num_tokens": 8544948.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 0.6268251063302159, |
| "epoch": 0.416, |
| "grad_norm": 43.5, |
| "learning_rate": 1.9913333333333335e-05, |
| "loss": 10.1171, |
| "mean_token_accuracy": 0.8166644174605608, |
| "num_tokens": 8627310.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 0.7168899232521653, |
| "epoch": 0.42, |
| "grad_norm": 45.0, |
| "learning_rate": 1.9891111111111112e-05, |
| "loss": 11.6477, |
| "mean_token_accuracy": 0.7963819321244955, |
| "num_tokens": 8707798.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.6254937417805195, |
| "epoch": 0.424, |
| "grad_norm": 39.5, |
| "learning_rate": 1.986888888888889e-05, |
| "loss": 10.0341, |
| "mean_token_accuracy": 0.8202919337898493, |
| "num_tokens": 8792574.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 0.6258060172200203, |
| "epoch": 0.428, |
| "grad_norm": 49.75, |
| "learning_rate": 1.9846666666666668e-05, |
| "loss": 10.2091, |
| "mean_token_accuracy": 0.8151731941848993, |
| "num_tokens": 8878637.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 0.6487020991742611, |
| "epoch": 0.432, |
| "grad_norm": 49.75, |
| "learning_rate": 1.9824444444444445e-05, |
| "loss": 10.4063, |
| "mean_token_accuracy": 0.8136575162410736, |
| "num_tokens": 8958371.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 0.6037185428664088, |
| "epoch": 0.436, |
| "grad_norm": 49.25, |
| "learning_rate": 1.9802222222222226e-05, |
| "loss": 9.8187, |
| "mean_token_accuracy": 0.8217611808329821, |
| "num_tokens": 9040649.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 0.5906071299687028, |
| "epoch": 0.44, |
| "grad_norm": 42.0, |
| "learning_rate": 1.978e-05, |
| "loss": 9.5257, |
| "mean_token_accuracy": 0.8266360804438591, |
| "num_tokens": 9125564.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_chemistry_entropy": 0.6296808683276176, |
| "eval_chemistry_loss": 0.6599302291870117, |
| "eval_chemistry_mean_token_accuracy": 0.8118611789941788, |
| "eval_chemistry_num_tokens": 9125564.0, |
| "eval_chemistry_runtime": 54.5116, |
| "eval_chemistry_samples_per_second": 9.172, |
| "eval_chemistry_steps_per_second": 9.172, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_physics_entropy": 0.6190407463014126, |
| "eval_physics_loss": 0.6459570527076721, |
| "eval_physics_mean_token_accuracy": 0.815562941968441, |
| "eval_physics_num_tokens": 9125564.0, |
| "eval_physics_runtime": 63.2267, |
| "eval_physics_samples_per_second": 7.908, |
| "eval_physics_steps_per_second": 7.908, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.6702354967594146, |
| "epoch": 0.444, |
| "grad_norm": 41.25, |
| "learning_rate": 1.975777777777778e-05, |
| "loss": 10.8062, |
| "mean_token_accuracy": 0.810298365727067, |
| "num_tokens": 9210443.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 0.6155520310625434, |
| "epoch": 0.448, |
| "grad_norm": 39.75, |
| "learning_rate": 1.9735555555555556e-05, |
| "loss": 10.1142, |
| "mean_token_accuracy": 0.8205059375613928, |
| "num_tokens": 9294388.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 0.5996189665980637, |
| "epoch": 0.452, |
| "grad_norm": 43.75, |
| "learning_rate": 1.9713333333333337e-05, |
| "loss": 9.4709, |
| "mean_token_accuracy": 0.8281105298548936, |
| "num_tokens": 9371203.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 0.6231001582928002, |
| "epoch": 0.456, |
| "grad_norm": 42.0, |
| "learning_rate": 1.969111111111111e-05, |
| "loss": 10.1464, |
| "mean_token_accuracy": 0.8164454229176045, |
| "num_tokens": 9455428.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 0.6021164663136005, |
| "epoch": 0.46, |
| "grad_norm": 39.0, |
| "learning_rate": 1.9668888888888892e-05, |
| "loss": 9.6895, |
| "mean_token_accuracy": 0.8233658988028765, |
| "num_tokens": 9539605.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.6290203684009612, |
| "epoch": 0.464, |
| "grad_norm": 42.0, |
| "learning_rate": 1.9646666666666666e-05, |
| "loss": 10.1725, |
| "mean_token_accuracy": 0.8175587739795447, |
| "num_tokens": 9620366.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 0.6108594150282443, |
| "epoch": 0.468, |
| "grad_norm": 51.75, |
| "learning_rate": 1.9624444444444447e-05, |
| "loss": 9.947, |
| "mean_token_accuracy": 0.819192311167717, |
| "num_tokens": 9706621.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 0.6204524893313647, |
| "epoch": 0.472, |
| "grad_norm": 39.5, |
| "learning_rate": 1.9602222222222225e-05, |
| "loss": 9.9455, |
| "mean_token_accuracy": 0.8174036685377359, |
| "num_tokens": 9788925.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 0.5935720985755324, |
| "epoch": 0.476, |
| "grad_norm": 36.5, |
| "learning_rate": 1.9580000000000002e-05, |
| "loss": 9.6394, |
| "mean_token_accuracy": 0.8253184624016285, |
| "num_tokens": 9869908.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 0.6630870910361409, |
| "epoch": 0.48, |
| "grad_norm": 47.0, |
| "learning_rate": 1.955777777777778e-05, |
| "loss": 10.7476, |
| "mean_token_accuracy": 0.808968411386013, |
| "num_tokens": 9955431.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_chemistry_entropy": 0.6792522894442081, |
| "eval_chemistry_loss": 0.6633003354072571, |
| "eval_chemistry_mean_token_accuracy": 0.8119940814971924, |
| "eval_chemistry_num_tokens": 9955431.0, |
| "eval_chemistry_runtime": 53.9215, |
| "eval_chemistry_samples_per_second": 9.273, |
| "eval_chemistry_steps_per_second": 9.273, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_physics_entropy": 0.650343769878149, |
| "eval_physics_loss": 0.6420111656188965, |
| "eval_physics_mean_token_accuracy": 0.8167362776398659, |
| "eval_physics_num_tokens": 9955431.0, |
| "eval_physics_runtime": 62.6062, |
| "eval_physics_samples_per_second": 7.986, |
| "eval_physics_steps_per_second": 7.986, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.612500429712236, |
| "epoch": 0.484, |
| "grad_norm": 47.0, |
| "learning_rate": 1.9535555555555557e-05, |
| "loss": 9.9347, |
| "mean_token_accuracy": 0.8223837319761514, |
| "num_tokens": 10038293.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 0.6377324659377337, |
| "epoch": 0.488, |
| "grad_norm": 40.5, |
| "learning_rate": 1.9513333333333335e-05, |
| "loss": 10.2831, |
| "mean_token_accuracy": 0.817806663736701, |
| "num_tokens": 10119599.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 0.6632728383876383, |
| "epoch": 0.492, |
| "grad_norm": 44.75, |
| "learning_rate": 1.9491111111111113e-05, |
| "loss": 10.6639, |
| "mean_token_accuracy": 0.80819180496037, |
| "num_tokens": 10204514.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 0.6558596555143594, |
| "epoch": 0.496, |
| "grad_norm": 36.0, |
| "learning_rate": 1.946888888888889e-05, |
| "loss": 10.5429, |
| "mean_token_accuracy": 0.8120821505784989, |
| "num_tokens": 10289883.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 0.6169624142348766, |
| "epoch": 0.5, |
| "grad_norm": 46.75, |
| "learning_rate": 1.9446666666666668e-05, |
| "loss": 10.0534, |
| "mean_token_accuracy": 0.8196999322623014, |
| "num_tokens": 10368762.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.6267159227281809, |
| "epoch": 0.504, |
| "grad_norm": 41.0, |
| "learning_rate": 1.9424444444444446e-05, |
| "loss": 10.096, |
| "mean_token_accuracy": 0.8189252704381943, |
| "num_tokens": 10454683.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 0.6419813117012382, |
| "epoch": 0.508, |
| "grad_norm": 42.0, |
| "learning_rate": 1.9402222222222223e-05, |
| "loss": 10.4847, |
| "mean_token_accuracy": 0.8120944950729608, |
| "num_tokens": 10539515.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 0.684658529702574, |
| "epoch": 0.512, |
| "grad_norm": 46.25, |
| "learning_rate": 1.938e-05, |
| "loss": 10.9876, |
| "mean_token_accuracy": 0.8051567550748586, |
| "num_tokens": 10619468.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 0.6482914222404361, |
| "epoch": 0.516, |
| "grad_norm": 42.75, |
| "learning_rate": 1.935777777777778e-05, |
| "loss": 10.3902, |
| "mean_token_accuracy": 0.8132968720048666, |
| "num_tokens": 10698439.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 0.6492844991385937, |
| "epoch": 0.52, |
| "grad_norm": 40.25, |
| "learning_rate": 1.9335555555555556e-05, |
| "loss": 10.5517, |
| "mean_token_accuracy": 0.809664323553443, |
| "num_tokens": 10781285.0, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_chemistry_entropy": 0.6645045831203461, |
| "eval_chemistry_loss": 0.6653202176094055, |
| "eval_chemistry_mean_token_accuracy": 0.811331033706665, |
| "eval_chemistry_num_tokens": 10781285.0, |
| "eval_chemistry_runtime": 55.4768, |
| "eval_chemistry_samples_per_second": 9.013, |
| "eval_chemistry_steps_per_second": 9.013, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_physics_entropy": 0.6388631807863713, |
| "eval_physics_loss": 0.6363136172294617, |
| "eval_physics_mean_token_accuracy": 0.8173955215811729, |
| "eval_physics_num_tokens": 10781285.0, |
| "eval_physics_runtime": 62.7946, |
| "eval_physics_samples_per_second": 7.962, |
| "eval_physics_steps_per_second": 7.962, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.6285697594285011, |
| "epoch": 0.524, |
| "grad_norm": 43.5, |
| "learning_rate": 1.9313333333333334e-05, |
| "loss": 10.221, |
| "mean_token_accuracy": 0.8181417305022478, |
| "num_tokens": 10864773.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 0.6136522050015628, |
| "epoch": 0.528, |
| "grad_norm": 38.0, |
| "learning_rate": 1.9291111111111115e-05, |
| "loss": 9.8866, |
| "mean_token_accuracy": 0.8212735544890165, |
| "num_tokens": 10944904.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 0.6457662120461464, |
| "epoch": 0.532, |
| "grad_norm": 45.75, |
| "learning_rate": 1.926888888888889e-05, |
| "loss": 10.3524, |
| "mean_token_accuracy": 0.8151355512440205, |
| "num_tokens": 11023958.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 0.5919691896066069, |
| "epoch": 0.536, |
| "grad_norm": 43.75, |
| "learning_rate": 1.924666666666667e-05, |
| "loss": 9.6708, |
| "mean_token_accuracy": 0.8262011889368296, |
| "num_tokens": 11106538.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 0.6490627369843424, |
| "epoch": 0.54, |
| "grad_norm": 51.75, |
| "learning_rate": 1.9224444444444444e-05, |
| "loss": 10.464, |
| "mean_token_accuracy": 0.8134491160511971, |
| "num_tokens": 11187142.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.6667550153099, |
| "epoch": 0.544, |
| "grad_norm": 54.5, |
| "learning_rate": 1.9202222222222225e-05, |
| "loss": 10.8278, |
| "mean_token_accuracy": 0.8061591122299433, |
| "num_tokens": 11266409.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 0.6294793977402151, |
| "epoch": 0.548, |
| "grad_norm": 48.5, |
| "learning_rate": 1.918e-05, |
| "loss": 10.153, |
| "mean_token_accuracy": 0.8186534035950899, |
| "num_tokens": 11350094.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 0.6307276577688754, |
| "epoch": 0.552, |
| "grad_norm": 46.5, |
| "learning_rate": 1.915777777777778e-05, |
| "loss": 10.2431, |
| "mean_token_accuracy": 0.8161013640463353, |
| "num_tokens": 11438391.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 0.6490003860555589, |
| "epoch": 0.556, |
| "grad_norm": 47.25, |
| "learning_rate": 1.9135555555555555e-05, |
| "loss": 10.292, |
| "mean_token_accuracy": 0.8154143560677767, |
| "num_tokens": 11521583.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 0.5914541745558382, |
| "epoch": 0.56, |
| "grad_norm": 41.0, |
| "learning_rate": 1.9113333333333336e-05, |
| "loss": 9.6568, |
| "mean_token_accuracy": 0.8256826549768448, |
| "num_tokens": 11605544.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_chemistry_entropy": 0.6548177749216556, |
| "eval_chemistry_loss": 0.6667582988739014, |
| "eval_chemistry_mean_token_accuracy": 0.8108637844324111, |
| "eval_chemistry_num_tokens": 11605544.0, |
| "eval_chemistry_runtime": 53.9633, |
| "eval_chemistry_samples_per_second": 9.266, |
| "eval_chemistry_steps_per_second": 9.266, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_physics_entropy": 0.6302824917435647, |
| "eval_physics_loss": 0.6326262354850769, |
| "eval_physics_mean_token_accuracy": 0.8184790652990341, |
| "eval_physics_num_tokens": 11605544.0, |
| "eval_physics_runtime": 62.6194, |
| "eval_physics_samples_per_second": 7.985, |
| "eval_physics_steps_per_second": 7.985, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.6050882572308183, |
| "epoch": 0.564, |
| "grad_norm": 39.25, |
| "learning_rate": 1.9091111111111113e-05, |
| "loss": 9.7547, |
| "mean_token_accuracy": 0.8240263950079679, |
| "num_tokens": 11686173.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 0.637587258964777, |
| "epoch": 0.568, |
| "grad_norm": 36.75, |
| "learning_rate": 1.906888888888889e-05, |
| "loss": 10.1842, |
| "mean_token_accuracy": 0.818510303273797, |
| "num_tokens": 11765430.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 0.6074552223086357, |
| "epoch": 0.572, |
| "grad_norm": 38.5, |
| "learning_rate": 1.904666666666667e-05, |
| "loss": 9.9644, |
| "mean_token_accuracy": 0.8220620211213827, |
| "num_tokens": 11850973.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 0.617229042109102, |
| "epoch": 0.576, |
| "grad_norm": 53.0, |
| "learning_rate": 1.9024444444444446e-05, |
| "loss": 9.9445, |
| "mean_token_accuracy": 0.820784068480134, |
| "num_tokens": 11931715.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 0.59880430418998, |
| "epoch": 0.58, |
| "grad_norm": 43.25, |
| "learning_rate": 1.9002222222222224e-05, |
| "loss": 9.5273, |
| "mean_token_accuracy": 0.8268065106123685, |
| "num_tokens": 12012155.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.6227379216812551, |
| "epoch": 0.584, |
| "grad_norm": 43.25, |
| "learning_rate": 1.898e-05, |
| "loss": 10.1233, |
| "mean_token_accuracy": 0.8189155597239732, |
| "num_tokens": 12093686.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 0.6201856574974954, |
| "epoch": 0.588, |
| "grad_norm": 41.75, |
| "learning_rate": 1.895777777777778e-05, |
| "loss": 9.9752, |
| "mean_token_accuracy": 0.8193617489188909, |
| "num_tokens": 12177581.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 0.6364695785567165, |
| "epoch": 0.592, |
| "grad_norm": 46.5, |
| "learning_rate": 1.8935555555555556e-05, |
| "loss": 10.3954, |
| "mean_token_accuracy": 0.8134158592671156, |
| "num_tokens": 12257243.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 0.6294575407169759, |
| "epoch": 0.596, |
| "grad_norm": 59.0, |
| "learning_rate": 1.8913333333333334e-05, |
| "loss": 10.1581, |
| "mean_token_accuracy": 0.8173588078469038, |
| "num_tokens": 12338544.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 0.6043597641400993, |
| "epoch": 0.6, |
| "grad_norm": 41.25, |
| "learning_rate": 1.8891111111111115e-05, |
| "loss": 9.7064, |
| "mean_token_accuracy": 0.8232355277985335, |
| "num_tokens": 12422008.0, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_chemistry_entropy": 0.6489740502238274, |
| "eval_chemistry_loss": 0.6658231019973755, |
| "eval_chemistry_mean_token_accuracy": 0.8121171447038651, |
| "eval_chemistry_num_tokens": 12422008.0, |
| "eval_chemistry_runtime": 53.9084, |
| "eval_chemistry_samples_per_second": 9.275, |
| "eval_chemistry_steps_per_second": 9.275, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_physics_entropy": 0.6161783193051815, |
| "eval_physics_loss": 0.628398597240448, |
| "eval_physics_mean_token_accuracy": 0.8198308848142624, |
| "eval_physics_num_tokens": 12422008.0, |
| "eval_physics_runtime": 62.5175, |
| "eval_physics_samples_per_second": 7.998, |
| "eval_physics_steps_per_second": 7.998, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.6060653101652861, |
| "epoch": 0.604, |
| "grad_norm": 42.75, |
| "learning_rate": 1.886888888888889e-05, |
| "loss": 9.894, |
| "mean_token_accuracy": 0.8234386540949344, |
| "num_tokens": 12505134.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 0.5880289922468365, |
| "epoch": 0.608, |
| "grad_norm": 50.75, |
| "learning_rate": 1.884666666666667e-05, |
| "loss": 9.4441, |
| "mean_token_accuracy": 0.8280234813690186, |
| "num_tokens": 12583154.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 0.625719802454114, |
| "epoch": 0.612, |
| "grad_norm": 41.0, |
| "learning_rate": 1.8824444444444445e-05, |
| "loss": 10.0379, |
| "mean_token_accuracy": 0.8188928976655007, |
| "num_tokens": 12666601.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 0.6189737745560706, |
| "epoch": 0.616, |
| "grad_norm": 39.0, |
| "learning_rate": 1.8802222222222226e-05, |
| "loss": 9.953, |
| "mean_token_accuracy": 0.8189409743994475, |
| "num_tokens": 12746458.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 0.6307426829822361, |
| "epoch": 0.62, |
| "grad_norm": 37.0, |
| "learning_rate": 1.878e-05, |
| "loss": 10.3275, |
| "mean_token_accuracy": 0.8165652919560671, |
| "num_tokens": 12831572.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.633724972512573, |
| "epoch": 0.624, |
| "grad_norm": 41.25, |
| "learning_rate": 1.875777777777778e-05, |
| "loss": 10.0729, |
| "mean_token_accuracy": 0.8192374683916569, |
| "num_tokens": 12905392.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 0.6234388993121683, |
| "epoch": 0.628, |
| "grad_norm": 44.25, |
| "learning_rate": 1.873555555555556e-05, |
| "loss": 10.1334, |
| "mean_token_accuracy": 0.8167661242187023, |
| "num_tokens": 12986513.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 0.6102577080950141, |
| "epoch": 0.632, |
| "grad_norm": 36.75, |
| "learning_rate": 1.8713333333333336e-05, |
| "loss": 9.8003, |
| "mean_token_accuracy": 0.8206873726099729, |
| "num_tokens": 13071058.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 0.6236647194251418, |
| "epoch": 0.636, |
| "grad_norm": 43.25, |
| "learning_rate": 1.8691111111111114e-05, |
| "loss": 10.1304, |
| "mean_token_accuracy": 0.816493471711874, |
| "num_tokens": 13151842.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 0.6845891922712326, |
| "epoch": 0.64, |
| "grad_norm": 45.75, |
| "learning_rate": 1.866888888888889e-05, |
| "loss": 11.213, |
| "mean_token_accuracy": 0.8044512301683426, |
| "num_tokens": 13232198.0, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_chemistry_entropy": 0.6778704892992974, |
| "eval_chemistry_loss": 0.6664143204689026, |
| "eval_chemistry_mean_token_accuracy": 0.8122610586881638, |
| "eval_chemistry_num_tokens": 13232198.0, |
| "eval_chemistry_runtime": 53.6359, |
| "eval_chemistry_samples_per_second": 9.322, |
| "eval_chemistry_steps_per_second": 9.322, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_physics_entropy": 0.6401235084533692, |
| "eval_physics_loss": 0.6214710474014282, |
| "eval_physics_mean_token_accuracy": 0.8208677229285241, |
| "eval_physics_num_tokens": 13232198.0, |
| "eval_physics_runtime": 62.3791, |
| "eval_physics_samples_per_second": 8.016, |
| "eval_physics_steps_per_second": 8.016, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.6061294285580516, |
| "epoch": 0.644, |
| "grad_norm": 41.5, |
| "learning_rate": 1.864666666666667e-05, |
| "loss": 9.6671, |
| "mean_token_accuracy": 0.8222626011818648, |
| "num_tokens": 13318037.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 0.6353385791182518, |
| "epoch": 0.648, |
| "grad_norm": 47.5, |
| "learning_rate": 1.8624444444444446e-05, |
| "loss": 10.2781, |
| "mean_token_accuracy": 0.8162215132266283, |
| "num_tokens": 13401064.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 0.6056097308173776, |
| "epoch": 0.652, |
| "grad_norm": 51.25, |
| "learning_rate": 1.8602222222222224e-05, |
| "loss": 9.9383, |
| "mean_token_accuracy": 0.8226072300225497, |
| "num_tokens": 13488222.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 0.6103159219957888, |
| "epoch": 0.656, |
| "grad_norm": 39.25, |
| "learning_rate": 1.858e-05, |
| "loss": 9.7041, |
| "mean_token_accuracy": 0.8251269839704036, |
| "num_tokens": 13575902.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 0.6257463837042451, |
| "epoch": 0.66, |
| "grad_norm": 38.75, |
| "learning_rate": 1.855777777777778e-05, |
| "loss": 10.1428, |
| "mean_token_accuracy": 0.8161589603871107, |
| "num_tokens": 13655826.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.6265889365226031, |
| "epoch": 0.664, |
| "grad_norm": 52.0, |
| "learning_rate": 1.8535555555555557e-05, |
| "loss": 10.1095, |
| "mean_token_accuracy": 0.8177770785987377, |
| "num_tokens": 13733192.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 0.5957706947810948, |
| "epoch": 0.668, |
| "grad_norm": 35.75, |
| "learning_rate": 1.8513333333333335e-05, |
| "loss": 9.5903, |
| "mean_token_accuracy": 0.8270833406597375, |
| "num_tokens": 13816716.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 0.6371551887132227, |
| "epoch": 0.672, |
| "grad_norm": 41.75, |
| "learning_rate": 1.8491111111111112e-05, |
| "loss": 10.4787, |
| "mean_token_accuracy": 0.8113816611468792, |
| "num_tokens": 13895997.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 0.5986419206485152, |
| "epoch": 0.676, |
| "grad_norm": 40.5, |
| "learning_rate": 1.846888888888889e-05, |
| "loss": 9.5155, |
| "mean_token_accuracy": 0.8267723452299833, |
| "num_tokens": 13988168.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 0.5948348139412701, |
| "epoch": 0.68, |
| "grad_norm": 43.5, |
| "learning_rate": 1.8446666666666667e-05, |
| "loss": 9.6889, |
| "mean_token_accuracy": 0.8268945027142763, |
| "num_tokens": 14074579.0, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_chemistry_entropy": 0.6539524466097355, |
| "eval_chemistry_loss": 0.6660082340240479, |
| "eval_chemistry_mean_token_accuracy": 0.8111258904933929, |
| "eval_chemistry_num_tokens": 14074579.0, |
| "eval_chemistry_runtime": 53.558, |
| "eval_chemistry_samples_per_second": 9.336, |
| "eval_chemistry_steps_per_second": 9.336, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_physics_entropy": 0.6102372957170009, |
| "eval_physics_loss": 0.6197578310966492, |
| "eval_physics_mean_token_accuracy": 0.8214541796445847, |
| "eval_physics_num_tokens": 14074579.0, |
| "eval_physics_runtime": 62.3426, |
| "eval_physics_samples_per_second": 8.02, |
| "eval_physics_steps_per_second": 8.02, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.6658952804282308, |
| "epoch": 0.684, |
| "grad_norm": 36.75, |
| "learning_rate": 1.842444444444445e-05, |
| "loss": 10.7562, |
| "mean_token_accuracy": 0.8074348546564579, |
| "num_tokens": 14153649.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 0.6083603931590915, |
| "epoch": 0.688, |
| "grad_norm": 41.5, |
| "learning_rate": 1.8402222222222223e-05, |
| "loss": 9.7355, |
| "mean_token_accuracy": 0.822414780780673, |
| "num_tokens": 14234888.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 0.6043023524805904, |
| "epoch": 0.692, |
| "grad_norm": 48.25, |
| "learning_rate": 1.8380000000000004e-05, |
| "loss": 9.8462, |
| "mean_token_accuracy": 0.8208967238664627, |
| "num_tokens": 14323183.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 0.613863595854491, |
| "epoch": 0.696, |
| "grad_norm": 42.25, |
| "learning_rate": 1.8357777777777778e-05, |
| "loss": 9.8414, |
| "mean_token_accuracy": 0.821249233186245, |
| "num_tokens": 14411150.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 0.6170497369021177, |
| "epoch": 0.7, |
| "grad_norm": 38.0, |
| "learning_rate": 1.833555555555556e-05, |
| "loss": 10.0544, |
| "mean_token_accuracy": 0.8183467876166105, |
| "num_tokens": 14490628.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.6329357607290149, |
| "epoch": 0.704, |
| "grad_norm": 43.75, |
| "learning_rate": 1.8313333333333333e-05, |
| "loss": 10.3231, |
| "mean_token_accuracy": 0.814619118347764, |
| "num_tokens": 14567908.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 0.6202297451905906, |
| "epoch": 0.708, |
| "grad_norm": 38.25, |
| "learning_rate": 1.8291111111111114e-05, |
| "loss": 9.8856, |
| "mean_token_accuracy": 0.8198208883404732, |
| "num_tokens": 14647291.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 0.5805901409126818, |
| "epoch": 0.712, |
| "grad_norm": 42.25, |
| "learning_rate": 1.8268888888888888e-05, |
| "loss": 9.4144, |
| "mean_token_accuracy": 0.8300752732902765, |
| "num_tokens": 14728975.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 0.6089818102307618, |
| "epoch": 0.716, |
| "grad_norm": 41.0, |
| "learning_rate": 1.824666666666667e-05, |
| "loss": 9.7038, |
| "mean_token_accuracy": 0.825373613089323, |
| "num_tokens": 14804586.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 0.6049615413881838, |
| "epoch": 0.72, |
| "grad_norm": 43.75, |
| "learning_rate": 1.8224444444444447e-05, |
| "loss": 9.9003, |
| "mean_token_accuracy": 0.8198985580354929, |
| "num_tokens": 14882927.0, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_chemistry_entropy": 0.6426224761903286, |
| "eval_chemistry_loss": 0.6654659509658813, |
| "eval_chemistry_mean_token_accuracy": 0.8117904326915741, |
| "eval_chemistry_num_tokens": 14882927.0, |
| "eval_chemistry_runtime": 53.7762, |
| "eval_chemistry_samples_per_second": 9.298, |
| "eval_chemistry_steps_per_second": 9.298, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_physics_entropy": 0.6037323722243308, |
| "eval_physics_loss": 0.616446316242218, |
| "eval_physics_mean_token_accuracy": 0.8222740324139595, |
| "eval_physics_num_tokens": 14882927.0, |
| "eval_physics_runtime": 62.498, |
| "eval_physics_samples_per_second": 8.0, |
| "eval_physics_steps_per_second": 8.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.6227391706779599, |
| "epoch": 0.724, |
| "grad_norm": 43.25, |
| "learning_rate": 1.8202222222222225e-05, |
| "loss": 9.9987, |
| "mean_token_accuracy": 0.818676395714283, |
| "num_tokens": 14966717.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 0.5725922109559178, |
| "epoch": 0.728, |
| "grad_norm": 42.5, |
| "learning_rate": 1.8180000000000002e-05, |
| "loss": 9.3114, |
| "mean_token_accuracy": 0.8298240959644317, |
| "num_tokens": 15052770.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 0.6312758250162005, |
| "epoch": 0.732, |
| "grad_norm": 35.0, |
| "learning_rate": 1.815777777777778e-05, |
| "loss": 10.2655, |
| "mean_token_accuracy": 0.8184621930122375, |
| "num_tokens": 15135882.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 0.6022148390300572, |
| "epoch": 0.736, |
| "grad_norm": 48.0, |
| "learning_rate": 1.8135555555555557e-05, |
| "loss": 9.6266, |
| "mean_token_accuracy": 0.8265880558639764, |
| "num_tokens": 15217342.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 0.6001213543117047, |
| "epoch": 0.74, |
| "grad_norm": 44.25, |
| "learning_rate": 1.8113333333333335e-05, |
| "loss": 9.7379, |
| "mean_token_accuracy": 0.8232456650584936, |
| "num_tokens": 15303623.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 0.5776225552894175, |
| "epoch": 0.744, |
| "grad_norm": 46.25, |
| "learning_rate": 1.8091111111111113e-05, |
| "loss": 9.2318, |
| "mean_token_accuracy": 0.8330205090343952, |
| "num_tokens": 15385161.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 0.6180003954097628, |
| "epoch": 0.748, |
| "grad_norm": 44.25, |
| "learning_rate": 1.806888888888889e-05, |
| "loss": 10.2082, |
| "mean_token_accuracy": 0.8174183562397956, |
| "num_tokens": 15466126.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 0.5681312756612897, |
| "epoch": 0.752, |
| "grad_norm": 44.75, |
| "learning_rate": 1.8046666666666668e-05, |
| "loss": 9.0644, |
| "mean_token_accuracy": 0.8345625158399343, |
| "num_tokens": 15547710.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 0.6220970245078206, |
| "epoch": 0.756, |
| "grad_norm": 46.25, |
| "learning_rate": 1.8024444444444445e-05, |
| "loss": 9.9613, |
| "mean_token_accuracy": 0.8187067184597254, |
| "num_tokens": 15625904.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 0.6236506992951035, |
| "epoch": 0.76, |
| "grad_norm": 43.75, |
| "learning_rate": 1.8002222222222223e-05, |
| "loss": 10.1366, |
| "mean_token_accuracy": 0.8179228503257037, |
| "num_tokens": 15704494.0, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_chemistry_entropy": 0.653880989164114, |
| "eval_chemistry_loss": 0.6663482189178467, |
| "eval_chemistry_mean_token_accuracy": 0.8113617711067199, |
| "eval_chemistry_num_tokens": 15704494.0, |
| "eval_chemistry_runtime": 53.799, |
| "eval_chemistry_samples_per_second": 9.294, |
| "eval_chemistry_steps_per_second": 9.294, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_physics_entropy": 0.6113817873895169, |
| "eval_physics_loss": 0.6128407716751099, |
| "eval_physics_mean_token_accuracy": 0.8226233792304992, |
| "eval_physics_num_tokens": 15704494.0, |
| "eval_physics_runtime": 62.4981, |
| "eval_physics_samples_per_second": 8.0, |
| "eval_physics_steps_per_second": 8.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 0.5962172176688909, |
| "epoch": 0.764, |
| "grad_norm": 37.0, |
| "learning_rate": 1.798e-05, |
| "loss": 9.5664, |
| "mean_token_accuracy": 0.8239004660397768, |
| "num_tokens": 15792219.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 0.5950108816847205, |
| "epoch": 0.768, |
| "grad_norm": 38.5, |
| "learning_rate": 1.7957777777777778e-05, |
| "loss": 9.6608, |
| "mean_token_accuracy": 0.8227977603673935, |
| "num_tokens": 15877177.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 0.5919695955701172, |
| "epoch": 0.772, |
| "grad_norm": 35.0, |
| "learning_rate": 1.7935555555555556e-05, |
| "loss": 9.5476, |
| "mean_token_accuracy": 0.8272939085960388, |
| "num_tokens": 15965749.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 0.6036200723610818, |
| "epoch": 0.776, |
| "grad_norm": 37.75, |
| "learning_rate": 1.7913333333333337e-05, |
| "loss": 9.7425, |
| "mean_token_accuracy": 0.8256110638380051, |
| "num_tokens": 16050530.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 0.6186987873166799, |
| "epoch": 0.78, |
| "grad_norm": 39.0, |
| "learning_rate": 1.789111111111111e-05, |
| "loss": 10.0185, |
| "mean_token_accuracy": 0.8216598622500897, |
| "num_tokens": 16136804.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 0.6003677137196064, |
| "epoch": 0.784, |
| "grad_norm": 42.5, |
| "learning_rate": 1.7868888888888892e-05, |
| "loss": 9.6501, |
| "mean_token_accuracy": 0.8250759091228247, |
| "num_tokens": 16219640.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 0.5993524115532637, |
| "epoch": 0.788, |
| "grad_norm": 42.5, |
| "learning_rate": 1.7846666666666666e-05, |
| "loss": 9.5775, |
| "mean_token_accuracy": 0.8249216306954622, |
| "num_tokens": 16299595.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 0.616146298404783, |
| "epoch": 0.792, |
| "grad_norm": 47.5, |
| "learning_rate": 1.7824444444444447e-05, |
| "loss": 10.0021, |
| "mean_token_accuracy": 0.8181390602141618, |
| "num_tokens": 16378820.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 0.6191745470277965, |
| "epoch": 0.796, |
| "grad_norm": 44.25, |
| "learning_rate": 1.780222222222222e-05, |
| "loss": 10.0675, |
| "mean_token_accuracy": 0.8181126184761525, |
| "num_tokens": 16464611.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 0.6169021054171026, |
| "epoch": 0.8, |
| "grad_norm": 34.5, |
| "learning_rate": 1.7780000000000003e-05, |
| "loss": 9.9317, |
| "mean_token_accuracy": 0.8213718693703413, |
| "num_tokens": 16548261.0, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_chemistry_entropy": 0.6557240565121174, |
| "eval_chemistry_loss": 0.6643321514129639, |
| "eval_chemistry_mean_token_accuracy": 0.810910725414753, |
| "eval_chemistry_num_tokens": 16548261.0, |
| "eval_chemistry_runtime": 53.5999, |
| "eval_chemistry_samples_per_second": 9.328, |
| "eval_chemistry_steps_per_second": 9.328, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_physics_entropy": 0.6022120754122734, |
| "eval_physics_loss": 0.6109762787818909, |
| "eval_physics_mean_token_accuracy": 0.8232671258449554, |
| "eval_physics_num_tokens": 16548261.0, |
| "eval_physics_runtime": 62.4211, |
| "eval_physics_samples_per_second": 8.01, |
| "eval_physics_steps_per_second": 8.01, |
| "step": 2000 |
| }, |
| { |
| "entropy": 0.5769328207708895, |
| "epoch": 0.804, |
| "grad_norm": 38.25, |
| "learning_rate": 1.7757777777777777e-05, |
| "loss": 9.3469, |
| "mean_token_accuracy": 0.8289602052420377, |
| "num_tokens": 16633428.0, |
| "step": 2010 |
| }, |
| { |
| "entropy": 0.639338431507349, |
| "epoch": 0.808, |
| "grad_norm": 38.75, |
| "learning_rate": 1.7735555555555558e-05, |
| "loss": 10.3607, |
| "mean_token_accuracy": 0.8114439073950053, |
| "num_tokens": 16711667.0, |
| "step": 2020 |
| }, |
| { |
| "entropy": 0.6080935266800225, |
| "epoch": 0.812, |
| "grad_norm": 37.5, |
| "learning_rate": 1.7713333333333335e-05, |
| "loss": 9.5741, |
| "mean_token_accuracy": 0.8260014273226262, |
| "num_tokens": 16789903.0, |
| "step": 2030 |
| }, |
| { |
| "entropy": 0.6141686610877514, |
| "epoch": 0.816, |
| "grad_norm": 34.0, |
| "learning_rate": 1.7691111111111113e-05, |
| "loss": 10.2542, |
| "mean_token_accuracy": 0.8148800980299711, |
| "num_tokens": 16870533.0, |
| "step": 2040 |
| }, |
| { |
| "entropy": 0.6198380364105105, |
| "epoch": 0.82, |
| "grad_norm": 42.0, |
| "learning_rate": 1.766888888888889e-05, |
| "loss": 9.8252, |
| "mean_token_accuracy": 0.8211232393980026, |
| "num_tokens": 16955146.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 0.6109458804130554, |
| "epoch": 0.824, |
| "grad_norm": 50.25, |
| "learning_rate": 1.7646666666666668e-05, |
| "loss": 9.9951, |
| "mean_token_accuracy": 0.8190602369606494, |
| "num_tokens": 17035600.0, |
| "step": 2060 |
| }, |
| { |
| "entropy": 0.616765193361789, |
| "epoch": 0.828, |
| "grad_norm": 42.0, |
| "learning_rate": 1.7624444444444446e-05, |
| "loss": 9.8759, |
| "mean_token_accuracy": 0.8201179711148143, |
| "num_tokens": 17114437.0, |
| "step": 2070 |
| }, |
| { |
| "entropy": 0.585936988517642, |
| "epoch": 0.832, |
| "grad_norm": 37.25, |
| "learning_rate": 1.7602222222222223e-05, |
| "loss": 9.4614, |
| "mean_token_accuracy": 0.8275429684668779, |
| "num_tokens": 17196371.0, |
| "step": 2080 |
| }, |
| { |
| "entropy": 0.6425325162708759, |
| "epoch": 0.836, |
| "grad_norm": 48.0, |
| "learning_rate": 1.758e-05, |
| "loss": 10.4242, |
| "mean_token_accuracy": 0.8143802944570779, |
| "num_tokens": 17277519.0, |
| "step": 2090 |
| }, |
| { |
| "entropy": 0.594513074401766, |
| "epoch": 0.84, |
| "grad_norm": 39.75, |
| "learning_rate": 1.755777777777778e-05, |
| "loss": 9.5434, |
| "mean_token_accuracy": 0.8270172599703074, |
| "num_tokens": 17356919.0, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_chemistry_entropy": 0.6422495054602623, |
| "eval_chemistry_loss": 0.6657618284225464, |
| "eval_chemistry_mean_token_accuracy": 0.8119068529605865, |
| "eval_chemistry_num_tokens": 17356919.0, |
| "eval_chemistry_runtime": 53.6953, |
| "eval_chemistry_samples_per_second": 9.312, |
| "eval_chemistry_steps_per_second": 9.312, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_physics_entropy": 0.5935313543379307, |
| "eval_physics_loss": 0.6082729697227478, |
| "eval_physics_mean_token_accuracy": 0.8237810920476913, |
| "eval_physics_num_tokens": 17356919.0, |
| "eval_physics_runtime": 62.7719, |
| "eval_physics_samples_per_second": 7.965, |
| "eval_physics_steps_per_second": 7.965, |
| "step": 2100 |
| }, |
| { |
| "entropy": 0.5766649033874274, |
| "epoch": 0.844, |
| "grad_norm": 36.75, |
| "learning_rate": 1.7535555555555556e-05, |
| "loss": 9.3985, |
| "mean_token_accuracy": 0.8289091024547816, |
| "num_tokens": 17438912.0, |
| "step": 2110 |
| }, |
| { |
| "entropy": 0.6027551379054785, |
| "epoch": 0.848, |
| "grad_norm": 41.5, |
| "learning_rate": 1.7513333333333334e-05, |
| "loss": 9.5153, |
| "mean_token_accuracy": 0.8274124126881361, |
| "num_tokens": 17527066.0, |
| "step": 2120 |
| }, |
| { |
| "entropy": 0.6090564800426364, |
| "epoch": 0.852, |
| "grad_norm": 36.25, |
| "learning_rate": 1.749111111111111e-05, |
| "loss": 9.9486, |
| "mean_token_accuracy": 0.8203190270811319, |
| "num_tokens": 17610559.0, |
| "step": 2130 |
| }, |
| { |
| "entropy": 0.6409425543621182, |
| "epoch": 0.856, |
| "grad_norm": 40.5, |
| "learning_rate": 1.746888888888889e-05, |
| "loss": 10.2511, |
| "mean_token_accuracy": 0.8137188758701086, |
| "num_tokens": 17689902.0, |
| "step": 2140 |
| }, |
| { |
| "entropy": 0.604229504428804, |
| "epoch": 0.86, |
| "grad_norm": 45.25, |
| "learning_rate": 1.7446666666666667e-05, |
| "loss": 9.8022, |
| "mean_token_accuracy": 0.8243927512317896, |
| "num_tokens": 17774080.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 0.608985879831016, |
| "epoch": 0.864, |
| "grad_norm": 39.75, |
| "learning_rate": 1.7424444444444444e-05, |
| "loss": 9.8919, |
| "mean_token_accuracy": 0.8220306746661663, |
| "num_tokens": 17859605.0, |
| "step": 2160 |
| }, |
| { |
| "entropy": 0.58911108141765, |
| "epoch": 0.868, |
| "grad_norm": 36.5, |
| "learning_rate": 1.7402222222222222e-05, |
| "loss": 9.4426, |
| "mean_token_accuracy": 0.8251889403909445, |
| "num_tokens": 17942040.0, |
| "step": 2170 |
| }, |
| { |
| "entropy": 0.6174473416060209, |
| "epoch": 0.872, |
| "grad_norm": 39.0, |
| "learning_rate": 1.7380000000000003e-05, |
| "loss": 9.9753, |
| "mean_token_accuracy": 0.8203635964542627, |
| "num_tokens": 18019924.0, |
| "step": 2180 |
| }, |
| { |
| "entropy": 0.6417605724185705, |
| "epoch": 0.876, |
| "grad_norm": 38.5, |
| "learning_rate": 1.735777777777778e-05, |
| "loss": 10.2624, |
| "mean_token_accuracy": 0.8150792047381401, |
| "num_tokens": 18102852.0, |
| "step": 2190 |
| }, |
| { |
| "entropy": 0.6028793597593903, |
| "epoch": 0.88, |
| "grad_norm": 46.25, |
| "learning_rate": 1.7335555555555558e-05, |
| "loss": 9.7194, |
| "mean_token_accuracy": 0.8240158323198556, |
| "num_tokens": 18187315.0, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_chemistry_entropy": 0.6486237399280071, |
| "eval_chemistry_loss": 0.6654757261276245, |
| "eval_chemistry_mean_token_accuracy": 0.812120854973793, |
| "eval_chemistry_num_tokens": 18187315.0, |
| "eval_chemistry_runtime": 54.4927, |
| "eval_chemistry_samples_per_second": 9.176, |
| "eval_chemistry_steps_per_second": 9.176, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_physics_entropy": 0.5944115283489227, |
| "eval_physics_loss": 0.6044148206710815, |
| "eval_physics_mean_token_accuracy": 0.8247024840712547, |
| "eval_physics_num_tokens": 18187315.0, |
| "eval_physics_runtime": 63.2321, |
| "eval_physics_samples_per_second": 7.907, |
| "eval_physics_steps_per_second": 7.907, |
| "step": 2200 |
| }, |
| { |
| "entropy": 0.5587692123837769, |
| "epoch": 0.884, |
| "grad_norm": 44.75, |
| "learning_rate": 1.7313333333333336e-05, |
| "loss": 9.1233, |
| "mean_token_accuracy": 0.8343214184045792, |
| "num_tokens": 18275135.0, |
| "step": 2210 |
| }, |
| { |
| "entropy": 0.5347248839214445, |
| "epoch": 0.888, |
| "grad_norm": 45.25, |
| "learning_rate": 1.7291111111111113e-05, |
| "loss": 8.4862, |
| "mean_token_accuracy": 0.8402233418077231, |
| "num_tokens": 18366329.0, |
| "step": 2220 |
| }, |
| { |
| "entropy": 0.6030035736039281, |
| "epoch": 0.892, |
| "grad_norm": 43.25, |
| "learning_rate": 1.726888888888889e-05, |
| "loss": 9.7969, |
| "mean_token_accuracy": 0.8230024907737971, |
| "num_tokens": 18449966.0, |
| "step": 2230 |
| }, |
| { |
| "entropy": 0.5451280565932393, |
| "epoch": 0.896, |
| "grad_norm": 35.75, |
| "learning_rate": 1.724666666666667e-05, |
| "loss": 8.8341, |
| "mean_token_accuracy": 0.836723905801773, |
| "num_tokens": 18536790.0, |
| "step": 2240 |
| }, |
| { |
| "entropy": 0.5979954308830202, |
| "epoch": 0.9, |
| "grad_norm": 35.75, |
| "learning_rate": 1.7224444444444446e-05, |
| "loss": 9.6096, |
| "mean_token_accuracy": 0.8243920177221298, |
| "num_tokens": 18619194.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 0.594355533272028, |
| "epoch": 0.904, |
| "grad_norm": 39.5, |
| "learning_rate": 1.7202222222222224e-05, |
| "loss": 9.5494, |
| "mean_token_accuracy": 0.8267385013401508, |
| "num_tokens": 18701809.0, |
| "step": 2260 |
| }, |
| { |
| "entropy": 0.6269824390299619, |
| "epoch": 0.908, |
| "grad_norm": 38.5, |
| "learning_rate": 1.718e-05, |
| "loss": 10.0915, |
| "mean_token_accuracy": 0.8181608844548464, |
| "num_tokens": 18785677.0, |
| "step": 2270 |
| }, |
| { |
| "entropy": 0.6125199305824935, |
| "epoch": 0.912, |
| "grad_norm": 37.25, |
| "learning_rate": 1.715777777777778e-05, |
| "loss": 9.9484, |
| "mean_token_accuracy": 0.818399741128087, |
| "num_tokens": 18869344.0, |
| "step": 2280 |
| }, |
| { |
| "entropy": 0.6096226529218256, |
| "epoch": 0.916, |
| "grad_norm": 35.25, |
| "learning_rate": 1.7135555555555557e-05, |
| "loss": 9.8473, |
| "mean_token_accuracy": 0.8235837988555431, |
| "num_tokens": 18954158.0, |
| "step": 2290 |
| }, |
| { |
| "entropy": 0.5883321419358254, |
| "epoch": 0.92, |
| "grad_norm": 51.75, |
| "learning_rate": 1.7113333333333334e-05, |
| "loss": 9.5237, |
| "mean_token_accuracy": 0.8259769681841135, |
| "num_tokens": 19033910.0, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.92, |
| "eval_chemistry_entropy": 0.6482902157604694, |
| "eval_chemistry_loss": 0.6630954742431641, |
| "eval_chemistry_mean_token_accuracy": 0.8121933689117432, |
| "eval_chemistry_num_tokens": 19033910.0, |
| "eval_chemistry_runtime": 53.6836, |
| "eval_chemistry_samples_per_second": 9.314, |
| "eval_chemistry_steps_per_second": 9.314, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.92, |
| "eval_physics_entropy": 0.5942936807274818, |
| "eval_physics_loss": 0.5992915034294128, |
| "eval_physics_mean_token_accuracy": 0.8255074183344842, |
| "eval_physics_num_tokens": 19033910.0, |
| "eval_physics_runtime": 62.5111, |
| "eval_physics_samples_per_second": 7.999, |
| "eval_physics_steps_per_second": 7.999, |
| "step": 2300 |
| }, |
| { |
| "entropy": 0.5868122247047722, |
| "epoch": 0.924, |
| "grad_norm": 39.0, |
| "learning_rate": 1.7091111111111112e-05, |
| "loss": 9.4248, |
| "mean_token_accuracy": 0.8281576413661241, |
| "num_tokens": 19116000.0, |
| "step": 2310 |
| }, |
| { |
| "entropy": 0.6330606296658516, |
| "epoch": 0.928, |
| "grad_norm": 42.25, |
| "learning_rate": 1.706888888888889e-05, |
| "loss": 10.0342, |
| "mean_token_accuracy": 0.8173846624791622, |
| "num_tokens": 19199834.0, |
| "step": 2320 |
| }, |
| { |
| "entropy": 0.5831953101791442, |
| "epoch": 0.932, |
| "grad_norm": 43.5, |
| "learning_rate": 1.704666666666667e-05, |
| "loss": 9.3531, |
| "mean_token_accuracy": 0.8273360066115856, |
| "num_tokens": 19277906.0, |
| "step": 2330 |
| }, |
| { |
| "entropy": 0.5802978583611548, |
| "epoch": 0.936, |
| "grad_norm": 39.75, |
| "learning_rate": 1.7024444444444445e-05, |
| "loss": 9.5706, |
| "mean_token_accuracy": 0.8274037476629019, |
| "num_tokens": 19361703.0, |
| "step": 2340 |
| }, |
| { |
| "entropy": 0.6136010095477105, |
| "epoch": 0.94, |
| "grad_norm": 34.75, |
| "learning_rate": 1.7002222222222226e-05, |
| "loss": 9.7159, |
| "mean_token_accuracy": 0.8238754648715257, |
| "num_tokens": 19444036.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 0.5773532028310001, |
| "epoch": 0.944, |
| "grad_norm": 41.75, |
| "learning_rate": 1.698e-05, |
| "loss": 9.3904, |
| "mean_token_accuracy": 0.8301644638180733, |
| "num_tokens": 19525385.0, |
| "step": 2360 |
| }, |
| { |
| "entropy": 0.5946352357976139, |
| "epoch": 0.948, |
| "grad_norm": 39.5, |
| "learning_rate": 1.695777777777778e-05, |
| "loss": 9.5084, |
| "mean_token_accuracy": 0.8257039908319712, |
| "num_tokens": 19606660.0, |
| "step": 2370 |
| }, |
| { |
| "entropy": 0.5877110615372658, |
| "epoch": 0.952, |
| "grad_norm": 42.25, |
| "learning_rate": 1.6935555555555555e-05, |
| "loss": 9.5004, |
| "mean_token_accuracy": 0.8257838502526283, |
| "num_tokens": 19690715.0, |
| "step": 2380 |
| }, |
| { |
| "entropy": 0.5759502210654318, |
| "epoch": 0.956, |
| "grad_norm": 41.0, |
| "learning_rate": 1.6913333333333336e-05, |
| "loss": 9.3654, |
| "mean_token_accuracy": 0.8302419554442168, |
| "num_tokens": 19773293.0, |
| "step": 2390 |
| }, |
| { |
| "entropy": 0.6265336956828833, |
| "epoch": 0.96, |
| "grad_norm": 36.25, |
| "learning_rate": 1.689111111111111e-05, |
| "loss": 10.1027, |
| "mean_token_accuracy": 0.8185567751526832, |
| "num_tokens": 19856973.0, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_chemistry_entropy": 0.6710790105164051, |
| "eval_chemistry_loss": 0.66240394115448, |
| "eval_chemistry_mean_token_accuracy": 0.8114456446170807, |
| "eval_chemistry_num_tokens": 19856973.0, |
| "eval_chemistry_runtime": 53.5716, |
| "eval_chemistry_samples_per_second": 9.333, |
| "eval_chemistry_steps_per_second": 9.333, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_physics_entropy": 0.6094872635900974, |
| "eval_physics_loss": 0.5976263284683228, |
| "eval_physics_mean_token_accuracy": 0.826532019495964, |
| "eval_physics_num_tokens": 19856973.0, |
| "eval_physics_runtime": 62.3185, |
| "eval_physics_samples_per_second": 8.023, |
| "eval_physics_steps_per_second": 8.023, |
| "step": 2400 |
| }, |
| { |
| "entropy": 0.5884977007284761, |
| "epoch": 0.964, |
| "grad_norm": 45.0, |
| "learning_rate": 1.686888888888889e-05, |
| "loss": 9.3858, |
| "mean_token_accuracy": 0.8279317501932383, |
| "num_tokens": 19939168.0, |
| "step": 2410 |
| }, |
| { |
| "entropy": 0.5823706248775125, |
| "epoch": 0.968, |
| "grad_norm": 42.75, |
| "learning_rate": 1.684666666666667e-05, |
| "loss": 9.5014, |
| "mean_token_accuracy": 0.8305404994636774, |
| "num_tokens": 20021093.0, |
| "step": 2420 |
| }, |
| { |
| "entropy": 0.574251430016011, |
| "epoch": 0.972, |
| "grad_norm": 39.75, |
| "learning_rate": 1.6824444444444447e-05, |
| "loss": 9.1394, |
| "mean_token_accuracy": 0.8329744711518288, |
| "num_tokens": 20109033.0, |
| "step": 2430 |
| }, |
| { |
| "entropy": 0.6081912533380092, |
| "epoch": 0.976, |
| "grad_norm": 44.25, |
| "learning_rate": 1.6802222222222224e-05, |
| "loss": 9.9884, |
| "mean_token_accuracy": 0.8211883638054133, |
| "num_tokens": 20190600.0, |
| "step": 2440 |
| }, |
| { |
| "entropy": 0.5859704153612256, |
| "epoch": 0.98, |
| "grad_norm": 39.5, |
| "learning_rate": 1.6780000000000002e-05, |
| "loss": 9.3289, |
| "mean_token_accuracy": 0.8274181935936212, |
| "num_tokens": 20269722.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 0.5964566855691373, |
| "epoch": 0.984, |
| "grad_norm": 43.0, |
| "learning_rate": 1.675777777777778e-05, |
| "loss": 9.6344, |
| "mean_token_accuracy": 0.8237358272075653, |
| "num_tokens": 20352255.0, |
| "step": 2460 |
| }, |
| { |
| "entropy": 0.5837171670980752, |
| "epoch": 0.988, |
| "grad_norm": 41.5, |
| "learning_rate": 1.6735555555555557e-05, |
| "loss": 9.4718, |
| "mean_token_accuracy": 0.8284726958721876, |
| "num_tokens": 20433069.0, |
| "step": 2470 |
| }, |
| { |
| "entropy": 0.5878238414414227, |
| "epoch": 0.992, |
| "grad_norm": 39.25, |
| "learning_rate": 1.6713333333333335e-05, |
| "loss": 9.5302, |
| "mean_token_accuracy": 0.8285502199083566, |
| "num_tokens": 20518014.0, |
| "step": 2480 |
| }, |
| { |
| "entropy": 0.5914754659868777, |
| "epoch": 0.996, |
| "grad_norm": 35.5, |
| "learning_rate": 1.6691111111111112e-05, |
| "loss": 9.4272, |
| "mean_token_accuracy": 0.8259847860783338, |
| "num_tokens": 20602688.0, |
| "step": 2490 |
| }, |
| { |
| "entropy": 0.565635210648179, |
| "epoch": 1.0, |
| "grad_norm": 44.75, |
| "learning_rate": 1.666888888888889e-05, |
| "loss": 9.1451, |
| "mean_token_accuracy": 0.8311932869255543, |
| "num_tokens": 20686804.0, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_chemistry_entropy": 0.6437437009811401, |
| "eval_chemistry_loss": 0.6624347567558289, |
| "eval_chemistry_mean_token_accuracy": 0.8123893816471099, |
| "eval_chemistry_num_tokens": 20686804.0, |
| "eval_chemistry_runtime": 53.5577, |
| "eval_chemistry_samples_per_second": 9.336, |
| "eval_chemistry_steps_per_second": 9.336, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_physics_entropy": 0.5847585182189942, |
| "eval_physics_loss": 0.5949397087097168, |
| "eval_physics_mean_token_accuracy": 0.8267857027053833, |
| "eval_physics_num_tokens": 20686804.0, |
| "eval_physics_runtime": 62.3711, |
| "eval_physics_samples_per_second": 8.017, |
| "eval_physics_steps_per_second": 8.017, |
| "step": 2500 |
| }, |
| { |
| "entropy": 0.43183089010417464, |
| "epoch": 1.004, |
| "grad_norm": 43.75, |
| "learning_rate": 1.6646666666666668e-05, |
| "loss": 6.4646, |
| "mean_token_accuracy": 0.8771685600280762, |
| "num_tokens": 20773982.0, |
| "step": 2510 |
| }, |
| { |
| "entropy": 0.3832437695004046, |
| "epoch": 1.008, |
| "grad_norm": 43.0, |
| "learning_rate": 1.6624444444444445e-05, |
| "loss": 6.4611, |
| "mean_token_accuracy": 0.878194584697485, |
| "num_tokens": 20859215.0, |
| "step": 2520 |
| }, |
| { |
| "entropy": 0.4238553931005299, |
| "epoch": 1.012, |
| "grad_norm": 71.5, |
| "learning_rate": 1.6602222222222223e-05, |
| "loss": 6.7028, |
| "mean_token_accuracy": 0.8725548766553402, |
| "num_tokens": 20939306.0, |
| "step": 2530 |
| }, |
| { |
| "entropy": 0.39157483652234076, |
| "epoch": 1.016, |
| "grad_norm": 42.0, |
| "learning_rate": 1.658e-05, |
| "loss": 6.2925, |
| "mean_token_accuracy": 0.8792892958968878, |
| "num_tokens": 21019542.0, |
| "step": 2540 |
| }, |
| { |
| "entropy": 0.3955075446516275, |
| "epoch": 1.02, |
| "grad_norm": 51.0, |
| "learning_rate": 1.6557777777777778e-05, |
| "loss": 6.4485, |
| "mean_token_accuracy": 0.8764517173171044, |
| "num_tokens": 21104882.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 0.41332366890273986, |
| "epoch": 1.024, |
| "grad_norm": 38.75, |
| "learning_rate": 1.6535555555555556e-05, |
| "loss": 6.582, |
| "mean_token_accuracy": 0.8762725710868835, |
| "num_tokens": 21186658.0, |
| "step": 2560 |
| }, |
| { |
| "entropy": 0.38238424006849525, |
| "epoch": 1.028, |
| "grad_norm": 44.25, |
| "learning_rate": 1.6513333333333333e-05, |
| "loss": 6.2961, |
| "mean_token_accuracy": 0.8797769464552403, |
| "num_tokens": 21268030.0, |
| "step": 2570 |
| }, |
| { |
| "entropy": 0.4287768125534058, |
| "epoch": 1.032, |
| "grad_norm": 44.5, |
| "learning_rate": 1.6491111111111114e-05, |
| "loss": 6.7601, |
| "mean_token_accuracy": 0.8724630124866962, |
| "num_tokens": 21351715.0, |
| "step": 2580 |
| }, |
| { |
| "entropy": 0.37041244744323193, |
| "epoch": 1.036, |
| "grad_norm": 46.75, |
| "learning_rate": 1.646888888888889e-05, |
| "loss": 6.1737, |
| "mean_token_accuracy": 0.8821764189749957, |
| "num_tokens": 21431494.0, |
| "step": 2590 |
| }, |
| { |
| "entropy": 0.41900953110307454, |
| "epoch": 1.04, |
| "grad_norm": 41.5, |
| "learning_rate": 1.644666666666667e-05, |
| "loss": 6.6902, |
| "mean_token_accuracy": 0.8732660066336393, |
| "num_tokens": 21517237.0, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_chemistry_entropy": 0.5526932182312012, |
| "eval_chemistry_loss": 0.6754207015037537, |
| "eval_chemistry_mean_token_accuracy": 0.8118693482875824, |
| "eval_chemistry_num_tokens": 21517237.0, |
| "eval_chemistry_runtime": 53.6728, |
| "eval_chemistry_samples_per_second": 9.316, |
| "eval_chemistry_steps_per_second": 9.316, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_physics_entropy": 0.5128993675708771, |
| "eval_physics_loss": 0.6065174341201782, |
| "eval_physics_mean_token_accuracy": 0.8264631150960923, |
| "eval_physics_num_tokens": 21517237.0, |
| "eval_physics_runtime": 62.4303, |
| "eval_physics_samples_per_second": 8.009, |
| "eval_physics_steps_per_second": 8.009, |
| "step": 2600 |
| }, |
| { |
| "entropy": 0.3923122527077794, |
| "epoch": 1.044, |
| "grad_norm": 52.5, |
| "learning_rate": 1.6424444444444444e-05, |
| "loss": 6.23, |
| "mean_token_accuracy": 0.882063326984644, |
| "num_tokens": 21597915.0, |
| "step": 2610 |
| }, |
| { |
| "entropy": 0.4064705569297075, |
| "epoch": 1.048, |
| "grad_norm": 36.25, |
| "learning_rate": 1.6402222222222225e-05, |
| "loss": 6.488, |
| "mean_token_accuracy": 0.8772788297384977, |
| "num_tokens": 21682780.0, |
| "step": 2620 |
| }, |
| { |
| "entropy": 0.38905340125784277, |
| "epoch": 1.052, |
| "grad_norm": 43.5, |
| "learning_rate": 1.638e-05, |
| "loss": 6.371, |
| "mean_token_accuracy": 0.8803388915956021, |
| "num_tokens": 21768676.0, |
| "step": 2630 |
| }, |
| { |
| "entropy": 0.3746905536390841, |
| "epoch": 1.056, |
| "grad_norm": 36.75, |
| "learning_rate": 1.635777777777778e-05, |
| "loss": 5.9046, |
| "mean_token_accuracy": 0.8856078766286373, |
| "num_tokens": 21852528.0, |
| "step": 2640 |
| }, |
| { |
| "entropy": 0.3955009472556412, |
| "epoch": 1.06, |
| "grad_norm": 46.25, |
| "learning_rate": 1.6335555555555558e-05, |
| "loss": 6.4522, |
| "mean_token_accuracy": 0.8777095880359411, |
| "num_tokens": 21939230.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 0.4184166899416596, |
| "epoch": 1.064, |
| "grad_norm": 41.5, |
| "learning_rate": 1.6313333333333335e-05, |
| "loss": 6.6604, |
| "mean_token_accuracy": 0.8737866301089525, |
| "num_tokens": 22021514.0, |
| "step": 2660 |
| }, |
| { |
| "entropy": 0.4157205421477556, |
| "epoch": 1.068, |
| "grad_norm": 44.0, |
| "learning_rate": 1.6291111111111113e-05, |
| "loss": 6.8267, |
| "mean_token_accuracy": 0.8705848950892687, |
| "num_tokens": 22106780.0, |
| "step": 2670 |
| }, |
| { |
| "entropy": 0.4116486982442439, |
| "epoch": 1.072, |
| "grad_norm": 35.75, |
| "learning_rate": 1.626888888888889e-05, |
| "loss": 6.48, |
| "mean_token_accuracy": 0.8772596288472414, |
| "num_tokens": 22192380.0, |
| "step": 2680 |
| }, |
| { |
| "entropy": 0.40143947368487715, |
| "epoch": 1.076, |
| "grad_norm": 46.75, |
| "learning_rate": 1.6246666666666668e-05, |
| "loss": 6.5291, |
| "mean_token_accuracy": 0.87435936704278, |
| "num_tokens": 22276772.0, |
| "step": 2690 |
| }, |
| { |
| "entropy": 0.4018312363885343, |
| "epoch": 1.08, |
| "grad_norm": 45.75, |
| "learning_rate": 1.6224444444444446e-05, |
| "loss": 6.2389, |
| "mean_token_accuracy": 0.879636450484395, |
| "num_tokens": 22356835.0, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.08, |
| "eval_chemistry_entropy": 0.528339877396822, |
| "eval_chemistry_loss": 0.6824756860733032, |
| "eval_chemistry_mean_token_accuracy": 0.810719025850296, |
| "eval_chemistry_num_tokens": 22356835.0, |
| "eval_chemistry_runtime": 54.3738, |
| "eval_chemistry_samples_per_second": 9.196, |
| "eval_chemistry_steps_per_second": 9.196, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.08, |
| "eval_physics_entropy": 0.48860630974173547, |
| "eval_physics_loss": 0.6100344061851501, |
| "eval_physics_mean_token_accuracy": 0.8260838712453842, |
| "eval_physics_num_tokens": 22356835.0, |
| "eval_physics_runtime": 62.4853, |
| "eval_physics_samples_per_second": 8.002, |
| "eval_physics_steps_per_second": 8.002, |
| "step": 2700 |
| }, |
| { |
| "entropy": 0.3871776068583131, |
| "epoch": 1.084, |
| "grad_norm": 38.5, |
| "learning_rate": 1.6202222222222223e-05, |
| "loss": 6.3317, |
| "mean_token_accuracy": 0.8779322851449252, |
| "num_tokens": 22438638.0, |
| "step": 2710 |
| }, |
| { |
| "entropy": 0.4119948163162917, |
| "epoch": 1.088, |
| "grad_norm": 59.75, |
| "learning_rate": 1.618e-05, |
| "loss": 6.6244, |
| "mean_token_accuracy": 0.8736134715378284, |
| "num_tokens": 22517971.0, |
| "step": 2720 |
| }, |
| { |
| "entropy": 0.39056964181363585, |
| "epoch": 1.092, |
| "grad_norm": 43.5, |
| "learning_rate": 1.615777777777778e-05, |
| "loss": 6.2406, |
| "mean_token_accuracy": 0.8803118593990803, |
| "num_tokens": 22599297.0, |
| "step": 2730 |
| }, |
| { |
| "entropy": 0.4071198822930455, |
| "epoch": 1.096, |
| "grad_norm": 45.0, |
| "learning_rate": 1.6135555555555556e-05, |
| "loss": 6.5373, |
| "mean_token_accuracy": 0.8748777855187655, |
| "num_tokens": 22681680.0, |
| "step": 2740 |
| }, |
| { |
| "entropy": 0.38830908089876176, |
| "epoch": 1.1, |
| "grad_norm": 42.5, |
| "learning_rate": 1.6113333333333334e-05, |
| "loss": 6.2908, |
| "mean_token_accuracy": 0.8802915759384632, |
| "num_tokens": 22768521.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 0.3899666819255799, |
| "epoch": 1.104, |
| "grad_norm": 35.0, |
| "learning_rate": 1.609111111111111e-05, |
| "loss": 6.1995, |
| "mean_token_accuracy": 0.8794200260192155, |
| "num_tokens": 22848694.0, |
| "step": 2760 |
| }, |
| { |
| "entropy": 0.3982271538116038, |
| "epoch": 1.108, |
| "grad_norm": 49.5, |
| "learning_rate": 1.606888888888889e-05, |
| "loss": 6.5132, |
| "mean_token_accuracy": 0.8748826995491982, |
| "num_tokens": 22934675.0, |
| "step": 2770 |
| }, |
| { |
| "entropy": 0.40925240265205504, |
| "epoch": 1.112, |
| "grad_norm": 41.0, |
| "learning_rate": 1.6046666666666667e-05, |
| "loss": 6.3908, |
| "mean_token_accuracy": 0.8794612839818001, |
| "num_tokens": 23016014.0, |
| "step": 2780 |
| }, |
| { |
| "entropy": 0.3979142210446298, |
| "epoch": 1.116, |
| "grad_norm": 42.5, |
| "learning_rate": 1.6024444444444444e-05, |
| "loss": 6.6062, |
| "mean_token_accuracy": 0.8738579101860523, |
| "num_tokens": 23099672.0, |
| "step": 2790 |
| }, |
| { |
| "entropy": 0.390972594358027, |
| "epoch": 1.12, |
| "grad_norm": 42.5, |
| "learning_rate": 1.6002222222222222e-05, |
| "loss": 6.0516, |
| "mean_token_accuracy": 0.8840138420462609, |
| "num_tokens": 23183889.0, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_chemistry_entropy": 0.5277839957475662, |
| "eval_chemistry_loss": 0.6832934617996216, |
| "eval_chemistry_mean_token_accuracy": 0.8105767689943314, |
| "eval_chemistry_num_tokens": 23183889.0, |
| "eval_chemistry_runtime": 53.7065, |
| "eval_chemistry_samples_per_second": 9.31, |
| "eval_chemistry_steps_per_second": 9.31, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_physics_entropy": 0.49138612353801725, |
| "eval_physics_loss": 0.6074111461639404, |
| "eval_physics_mean_token_accuracy": 0.8264175375699997, |
| "eval_physics_num_tokens": 23183889.0, |
| "eval_physics_runtime": 62.3744, |
| "eval_physics_samples_per_second": 8.016, |
| "eval_physics_steps_per_second": 8.016, |
| "step": 2800 |
| }, |
| { |
| "entropy": 0.35932957073673605, |
| "epoch": 1.124, |
| "grad_norm": 43.75, |
| "learning_rate": 1.5980000000000003e-05, |
| "loss": 6.0668, |
| "mean_token_accuracy": 0.8830338750034571, |
| "num_tokens": 23273263.0, |
| "step": 2810 |
| }, |
| { |
| "entropy": 0.3861358379013836, |
| "epoch": 1.1280000000000001, |
| "grad_norm": 49.75, |
| "learning_rate": 1.5957777777777777e-05, |
| "loss": 6.0376, |
| "mean_token_accuracy": 0.8845888160169124, |
| "num_tokens": 23354096.0, |
| "step": 2820 |
| }, |
| { |
| "entropy": 0.3910831346176565, |
| "epoch": 1.1320000000000001, |
| "grad_norm": 40.5, |
| "learning_rate": 1.5935555555555558e-05, |
| "loss": 6.3203, |
| "mean_token_accuracy": 0.8786633264273405, |
| "num_tokens": 23435009.0, |
| "step": 2830 |
| }, |
| { |
| "entropy": 0.39575566886924207, |
| "epoch": 1.1360000000000001, |
| "grad_norm": 39.25, |
| "learning_rate": 1.5913333333333332e-05, |
| "loss": 6.4965, |
| "mean_token_accuracy": 0.8768609743565321, |
| "num_tokens": 23523903.0, |
| "step": 2840 |
| }, |
| { |
| "entropy": 0.41750739673152565, |
| "epoch": 1.1400000000000001, |
| "grad_norm": 43.25, |
| "learning_rate": 1.5891111111111113e-05, |
| "loss": 6.597, |
| "mean_token_accuracy": 0.8746554154902697, |
| "num_tokens": 23609422.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 0.40066886888816955, |
| "epoch": 1.144, |
| "grad_norm": 41.25, |
| "learning_rate": 1.5868888888888888e-05, |
| "loss": 6.5186, |
| "mean_token_accuracy": 0.8758725844323635, |
| "num_tokens": 23684571.0, |
| "step": 2860 |
| }, |
| { |
| "entropy": 0.4339528376236558, |
| "epoch": 1.148, |
| "grad_norm": 40.0, |
| "learning_rate": 1.584666666666667e-05, |
| "loss": 6.9187, |
| "mean_token_accuracy": 0.8712858468294143, |
| "num_tokens": 23772422.0, |
| "step": 2870 |
| }, |
| { |
| "entropy": 0.407416142616421, |
| "epoch": 1.152, |
| "grad_norm": 39.25, |
| "learning_rate": 1.5824444444444446e-05, |
| "loss": 6.623, |
| "mean_token_accuracy": 0.8760526139289141, |
| "num_tokens": 23848848.0, |
| "step": 2880 |
| }, |
| { |
| "entropy": 0.41878221230581403, |
| "epoch": 1.156, |
| "grad_norm": 38.0, |
| "learning_rate": 1.5802222222222224e-05, |
| "loss": 6.6909, |
| "mean_token_accuracy": 0.8737323805689812, |
| "num_tokens": 23927139.0, |
| "step": 2890 |
| }, |
| { |
| "entropy": 0.3954612009227276, |
| "epoch": 1.16, |
| "grad_norm": 48.25, |
| "learning_rate": 1.578e-05, |
| "loss": 6.3773, |
| "mean_token_accuracy": 0.8771356221288442, |
| "num_tokens": 24011654.0, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.16, |
| "eval_chemistry_entropy": 0.5298384475111961, |
| "eval_chemistry_loss": 0.6839735507965088, |
| "eval_chemistry_mean_token_accuracy": 0.8118355718851089, |
| "eval_chemistry_num_tokens": 24011654.0, |
| "eval_chemistry_runtime": 53.5702, |
| "eval_chemistry_samples_per_second": 9.334, |
| "eval_chemistry_steps_per_second": 9.334, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.16, |
| "eval_physics_entropy": 0.4960176517665386, |
| "eval_physics_loss": 0.6066020131111145, |
| "eval_physics_mean_token_accuracy": 0.8260394994020462, |
| "eval_physics_num_tokens": 24011654.0, |
| "eval_physics_runtime": 62.3484, |
| "eval_physics_samples_per_second": 8.019, |
| "eval_physics_steps_per_second": 8.019, |
| "step": 2900 |
| }, |
| { |
| "entropy": 0.38181931935250757, |
| "epoch": 1.164, |
| "grad_norm": 43.25, |
| "learning_rate": 1.575777777777778e-05, |
| "loss": 6.1702, |
| "mean_token_accuracy": 0.8803447645157576, |
| "num_tokens": 24090340.0, |
| "step": 2910 |
| }, |
| { |
| "entropy": 0.41627788487821815, |
| "epoch": 1.168, |
| "grad_norm": 54.75, |
| "learning_rate": 1.5735555555555557e-05, |
| "loss": 6.6549, |
| "mean_token_accuracy": 0.8718316704034805, |
| "num_tokens": 24174589.0, |
| "step": 2920 |
| }, |
| { |
| "entropy": 0.3925532539375126, |
| "epoch": 1.172, |
| "grad_norm": 49.75, |
| "learning_rate": 1.5713333333333334e-05, |
| "loss": 6.2928, |
| "mean_token_accuracy": 0.8777770098298788, |
| "num_tokens": 24256063.0, |
| "step": 2930 |
| }, |
| { |
| "entropy": 0.43556569516658783, |
| "epoch": 1.176, |
| "grad_norm": 43.75, |
| "learning_rate": 1.5691111111111112e-05, |
| "loss": 7.023, |
| "mean_token_accuracy": 0.8686692509800196, |
| "num_tokens": 24336249.0, |
| "step": 2940 |
| }, |
| { |
| "entropy": 0.3898361031897366, |
| "epoch": 1.18, |
| "grad_norm": 36.5, |
| "learning_rate": 1.5668888888888893e-05, |
| "loss": 6.1418, |
| "mean_token_accuracy": 0.8812136992812156, |
| "num_tokens": 24415615.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 0.37849364345893266, |
| "epoch": 1.184, |
| "grad_norm": 42.5, |
| "learning_rate": 1.5646666666666667e-05, |
| "loss": 6.2013, |
| "mean_token_accuracy": 0.8820504449307919, |
| "num_tokens": 24495981.0, |
| "step": 2960 |
| }, |
| { |
| "entropy": 0.4079933548346162, |
| "epoch": 1.188, |
| "grad_norm": 49.0, |
| "learning_rate": 1.5624444444444448e-05, |
| "loss": 6.6523, |
| "mean_token_accuracy": 0.8723030515015125, |
| "num_tokens": 24575688.0, |
| "step": 2970 |
| }, |
| { |
| "entropy": 0.3756624376401305, |
| "epoch": 1.192, |
| "grad_norm": 42.0, |
| "learning_rate": 1.5602222222222222e-05, |
| "loss": 5.8133, |
| "mean_token_accuracy": 0.8876727018505335, |
| "num_tokens": 24658862.0, |
| "step": 2980 |
| }, |
| { |
| "entropy": 0.3933048089966178, |
| "epoch": 1.196, |
| "grad_norm": 43.25, |
| "learning_rate": 1.5580000000000003e-05, |
| "loss": 6.577, |
| "mean_token_accuracy": 0.8762084610760212, |
| "num_tokens": 24742908.0, |
| "step": 2990 |
| }, |
| { |
| "entropy": 0.41905345749109985, |
| "epoch": 1.2, |
| "grad_norm": 51.0, |
| "learning_rate": 1.5557777777777778e-05, |
| "loss": 6.5299, |
| "mean_token_accuracy": 0.8759240590035915, |
| "num_tokens": 24826245.0, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_chemistry_entropy": 0.5453705522418022, |
| "eval_chemistry_loss": 0.6793319582939148, |
| "eval_chemistry_mean_token_accuracy": 0.8109741320610047, |
| "eval_chemistry_num_tokens": 24826245.0, |
| "eval_chemistry_runtime": 53.5792, |
| "eval_chemistry_samples_per_second": 9.332, |
| "eval_chemistry_steps_per_second": 9.332, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_physics_entropy": 0.5037744672298431, |
| "eval_physics_loss": 0.6024576425552368, |
| "eval_physics_mean_token_accuracy": 0.8275209935307503, |
| "eval_physics_num_tokens": 24826245.0, |
| "eval_physics_runtime": 62.4678, |
| "eval_physics_samples_per_second": 8.004, |
| "eval_physics_steps_per_second": 8.004, |
| "step": 3000 |
| }, |
| { |
| "entropy": 0.3997825036756694, |
| "epoch": 1.204, |
| "grad_norm": 37.5, |
| "learning_rate": 1.553555555555556e-05, |
| "loss": 6.5565, |
| "mean_token_accuracy": 0.8763858702033758, |
| "num_tokens": 24909586.0, |
| "step": 3010 |
| }, |
| { |
| "entropy": 0.38890892546623945, |
| "epoch": 1.208, |
| "grad_norm": 49.75, |
| "learning_rate": 1.5513333333333333e-05, |
| "loss": 6.2919, |
| "mean_token_accuracy": 0.88029565513134, |
| "num_tokens": 24988821.0, |
| "step": 3020 |
| }, |
| { |
| "entropy": 0.4091858469881117, |
| "epoch": 1.212, |
| "grad_norm": 51.25, |
| "learning_rate": 1.5491111111111114e-05, |
| "loss": 6.5897, |
| "mean_token_accuracy": 0.8751243494451046, |
| "num_tokens": 25069416.0, |
| "step": 3030 |
| }, |
| { |
| "entropy": 0.4264195324853063, |
| "epoch": 1.216, |
| "grad_norm": 54.25, |
| "learning_rate": 1.546888888888889e-05, |
| "loss": 6.8662, |
| "mean_token_accuracy": 0.869670495390892, |
| "num_tokens": 25147775.0, |
| "step": 3040 |
| }, |
| { |
| "entropy": 0.3972005158662796, |
| "epoch": 1.22, |
| "grad_norm": 46.0, |
| "learning_rate": 1.544666666666667e-05, |
| "loss": 6.4659, |
| "mean_token_accuracy": 0.8787313677370548, |
| "num_tokens": 25228447.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 0.42326033059507606, |
| "epoch": 1.224, |
| "grad_norm": 43.0, |
| "learning_rate": 1.5424444444444447e-05, |
| "loss": 6.635, |
| "mean_token_accuracy": 0.8740264683961868, |
| "num_tokens": 25312652.0, |
| "step": 3060 |
| }, |
| { |
| "entropy": 0.3997484935447574, |
| "epoch": 1.228, |
| "grad_norm": 37.5, |
| "learning_rate": 1.5402222222222224e-05, |
| "loss": 6.4985, |
| "mean_token_accuracy": 0.8779609993100166, |
| "num_tokens": 25395706.0, |
| "step": 3070 |
| }, |
| { |
| "entropy": 0.4184209566563368, |
| "epoch": 1.232, |
| "grad_norm": 46.5, |
| "learning_rate": 1.5380000000000002e-05, |
| "loss": 6.6546, |
| "mean_token_accuracy": 0.8734137929975987, |
| "num_tokens": 25480033.0, |
| "step": 3080 |
| }, |
| { |
| "entropy": 0.3735330808442086, |
| "epoch": 1.236, |
| "grad_norm": 38.75, |
| "learning_rate": 1.535777777777778e-05, |
| "loss": 6.165, |
| "mean_token_accuracy": 0.8828396521508693, |
| "num_tokens": 25559873.0, |
| "step": 3090 |
| }, |
| { |
| "entropy": 0.3877786135300994, |
| "epoch": 1.24, |
| "grad_norm": 44.25, |
| "learning_rate": 1.5335555555555557e-05, |
| "loss": 6.1214, |
| "mean_token_accuracy": 0.8815136577934026, |
| "num_tokens": 25643821.0, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.24, |
| "eval_chemistry_entropy": 0.5628473788201809, |
| "eval_chemistry_loss": 0.6753941774368286, |
| "eval_chemistry_mean_token_accuracy": 0.8121462626457214, |
| "eval_chemistry_num_tokens": 25643821.0, |
| "eval_chemistry_runtime": 53.6798, |
| "eval_chemistry_samples_per_second": 9.314, |
| "eval_chemistry_steps_per_second": 9.314, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.24, |
| "eval_physics_entropy": 0.5132348291277885, |
| "eval_physics_loss": 0.5996105074882507, |
| "eval_physics_mean_token_accuracy": 0.8279496403336525, |
| "eval_physics_num_tokens": 25643821.0, |
| "eval_physics_runtime": 62.4176, |
| "eval_physics_samples_per_second": 8.011, |
| "eval_physics_steps_per_second": 8.011, |
| "step": 3100 |
| }, |
| { |
| "entropy": 0.3988831571303308, |
| "epoch": 1.244, |
| "grad_norm": 53.0, |
| "learning_rate": 1.5313333333333335e-05, |
| "loss": 6.3279, |
| "mean_token_accuracy": 0.8781545918434859, |
| "num_tokens": 25725796.0, |
| "step": 3110 |
| }, |
| { |
| "entropy": 0.39984851367771623, |
| "epoch": 1.248, |
| "grad_norm": 50.0, |
| "learning_rate": 1.5291111111111112e-05, |
| "loss": 6.6278, |
| "mean_token_accuracy": 0.8735591024160385, |
| "num_tokens": 25811978.0, |
| "step": 3120 |
| }, |
| { |
| "entropy": 0.42747304858639834, |
| "epoch": 1.252, |
| "grad_norm": 54.25, |
| "learning_rate": 1.526888888888889e-05, |
| "loss": 6.744, |
| "mean_token_accuracy": 0.873236209899187, |
| "num_tokens": 25889082.0, |
| "step": 3130 |
| }, |
| { |
| "entropy": 0.3893546565435827, |
| "epoch": 1.256, |
| "grad_norm": 45.5, |
| "learning_rate": 1.5246666666666668e-05, |
| "loss": 6.2849, |
| "mean_token_accuracy": 0.8787511799484491, |
| "num_tokens": 25980217.0, |
| "step": 3140 |
| }, |
| { |
| "entropy": 0.3870727655477822, |
| "epoch": 1.26, |
| "grad_norm": 49.75, |
| "learning_rate": 1.5224444444444447e-05, |
| "loss": 6.2027, |
| "mean_token_accuracy": 0.8804555464535951, |
| "num_tokens": 26064259.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 0.3931499463506043, |
| "epoch": 1.264, |
| "grad_norm": 47.75, |
| "learning_rate": 1.5202222222222223e-05, |
| "loss": 6.2611, |
| "mean_token_accuracy": 0.8800795335322619, |
| "num_tokens": 26146299.0, |
| "step": 3160 |
| }, |
| { |
| "entropy": 0.4023557474836707, |
| "epoch": 1.268, |
| "grad_norm": 47.0, |
| "learning_rate": 1.5180000000000002e-05, |
| "loss": 6.3743, |
| "mean_token_accuracy": 0.8788915742188692, |
| "num_tokens": 26224759.0, |
| "step": 3170 |
| }, |
| { |
| "entropy": 0.39270303705707194, |
| "epoch": 1.272, |
| "grad_norm": 40.75, |
| "learning_rate": 1.5157777777777778e-05, |
| "loss": 6.423, |
| "mean_token_accuracy": 0.8762969862669706, |
| "num_tokens": 26315594.0, |
| "step": 3180 |
| }, |
| { |
| "entropy": 0.43091254495084286, |
| "epoch": 1.276, |
| "grad_norm": 49.75, |
| "learning_rate": 1.5135555555555557e-05, |
| "loss": 6.909, |
| "mean_token_accuracy": 0.8699054338037968, |
| "num_tokens": 26394622.0, |
| "step": 3190 |
| }, |
| { |
| "entropy": 0.43948563635349275, |
| "epoch": 1.28, |
| "grad_norm": 54.25, |
| "learning_rate": 1.5113333333333335e-05, |
| "loss": 7.0251, |
| "mean_token_accuracy": 0.8672812581062317, |
| "num_tokens": 26478207.0, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_chemistry_entropy": 0.5399982813298703, |
| "eval_chemistry_loss": 0.6762998104095459, |
| "eval_chemistry_mean_token_accuracy": 0.8126340419054031, |
| "eval_chemistry_num_tokens": 26478207.0, |
| "eval_chemistry_runtime": 53.9132, |
| "eval_chemistry_samples_per_second": 9.274, |
| "eval_chemistry_steps_per_second": 9.274, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.28, |
| "eval_physics_entropy": 0.5009064598977566, |
| "eval_physics_loss": 0.5996403694152832, |
| "eval_physics_mean_token_accuracy": 0.828355691075325, |
| "eval_physics_num_tokens": 26478207.0, |
| "eval_physics_runtime": 62.7825, |
| "eval_physics_samples_per_second": 7.964, |
| "eval_physics_steps_per_second": 7.964, |
| "step": 3200 |
| }, |
| { |
| "entropy": 0.3829960603266954, |
| "epoch": 1.284, |
| "grad_norm": 55.25, |
| "learning_rate": 1.5091111111111113e-05, |
| "loss": 6.1965, |
| "mean_token_accuracy": 0.8819497369229794, |
| "num_tokens": 26565510.0, |
| "step": 3210 |
| }, |
| { |
| "entropy": 0.4178653988055885, |
| "epoch": 1.288, |
| "grad_norm": 51.5, |
| "learning_rate": 1.506888888888889e-05, |
| "loss": 6.6563, |
| "mean_token_accuracy": 0.8736223887652159, |
| "num_tokens": 26647567.0, |
| "step": 3220 |
| }, |
| { |
| "entropy": 0.36892555058002474, |
| "epoch": 1.292, |
| "grad_norm": 38.0, |
| "learning_rate": 1.5046666666666668e-05, |
| "loss": 5.88, |
| "mean_token_accuracy": 0.8862396698445082, |
| "num_tokens": 26725591.0, |
| "step": 3230 |
| }, |
| { |
| "entropy": 0.43142272820696237, |
| "epoch": 1.296, |
| "grad_norm": 51.0, |
| "learning_rate": 1.5024444444444445e-05, |
| "loss": 7.2241, |
| "mean_token_accuracy": 0.8642895489931106, |
| "num_tokens": 26806477.0, |
| "step": 3240 |
| }, |
| { |
| "entropy": 0.4274237054400146, |
| "epoch": 1.3, |
| "grad_norm": 46.25, |
| "learning_rate": 1.5002222222222223e-05, |
| "loss": 6.6789, |
| "mean_token_accuracy": 0.8733241800218821, |
| "num_tokens": 26889441.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 0.40652468013577164, |
| "epoch": 1.304, |
| "grad_norm": 41.75, |
| "learning_rate": 1.498e-05, |
| "loss": 6.6179, |
| "mean_token_accuracy": 0.8742008306086063, |
| "num_tokens": 26973124.0, |
| "step": 3260 |
| }, |
| { |
| "entropy": 0.42686001770198345, |
| "epoch": 1.308, |
| "grad_norm": 45.0, |
| "learning_rate": 1.495777777777778e-05, |
| "loss": 6.7405, |
| "mean_token_accuracy": 0.8706731535494328, |
| "num_tokens": 27055996.0, |
| "step": 3270 |
| }, |
| { |
| "entropy": 0.37794668129645287, |
| "epoch": 1.312, |
| "grad_norm": 50.5, |
| "learning_rate": 1.4935555555555556e-05, |
| "loss": 6.1894, |
| "mean_token_accuracy": 0.8806595619767904, |
| "num_tokens": 27137528.0, |
| "step": 3280 |
| }, |
| { |
| "entropy": 0.40770810479298236, |
| "epoch": 1.316, |
| "grad_norm": 53.5, |
| "learning_rate": 1.4913333333333335e-05, |
| "loss": 6.4258, |
| "mean_token_accuracy": 0.8776110667735338, |
| "num_tokens": 27217725.0, |
| "step": 3290 |
| }, |
| { |
| "entropy": 0.3946953667793423, |
| "epoch": 1.32, |
| "grad_norm": 37.25, |
| "learning_rate": 1.4891111111111111e-05, |
| "loss": 6.2872, |
| "mean_token_accuracy": 0.878388949483633, |
| "num_tokens": 27300986.0, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.32, |
| "eval_chemistry_entropy": 0.5206425618231296, |
| "eval_chemistry_loss": 0.6836199760437012, |
| "eval_chemistry_mean_token_accuracy": 0.8110970590114593, |
| "eval_chemistry_num_tokens": 27300986.0, |
| "eval_chemistry_runtime": 53.7324, |
| "eval_chemistry_samples_per_second": 9.305, |
| "eval_chemistry_steps_per_second": 9.305, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.32, |
| "eval_physics_entropy": 0.49023931473493576, |
| "eval_physics_loss": 0.601118266582489, |
| "eval_physics_mean_token_accuracy": 0.8291674974560738, |
| "eval_physics_num_tokens": 27300986.0, |
| "eval_physics_runtime": 62.4572, |
| "eval_physics_samples_per_second": 8.005, |
| "eval_physics_steps_per_second": 8.005, |
| "step": 3300 |
| }, |
| { |
| "entropy": 0.41491028452292084, |
| "epoch": 1.324, |
| "grad_norm": 46.0, |
| "learning_rate": 1.486888888888889e-05, |
| "loss": 6.8186, |
| "mean_token_accuracy": 0.871044621989131, |
| "num_tokens": 27382547.0, |
| "step": 3310 |
| }, |
| { |
| "entropy": 0.39110199781134725, |
| "epoch": 1.328, |
| "grad_norm": 39.75, |
| "learning_rate": 1.4846666666666666e-05, |
| "loss": 6.2792, |
| "mean_token_accuracy": 0.8789916034787894, |
| "num_tokens": 27465859.0, |
| "step": 3320 |
| }, |
| { |
| "entropy": 0.38766958490014075, |
| "epoch": 1.332, |
| "grad_norm": 50.25, |
| "learning_rate": 1.4824444444444446e-05, |
| "loss": 6.197, |
| "mean_token_accuracy": 0.8813134826719761, |
| "num_tokens": 27545600.0, |
| "step": 3330 |
| }, |
| { |
| "entropy": 0.39093358917161825, |
| "epoch": 1.336, |
| "grad_norm": 63.75, |
| "learning_rate": 1.4802222222222225e-05, |
| "loss": 6.2033, |
| "mean_token_accuracy": 0.8811442971229553, |
| "num_tokens": 27627148.0, |
| "step": 3340 |
| }, |
| { |
| "entropy": 0.40219460977241395, |
| "epoch": 1.34, |
| "grad_norm": 53.25, |
| "learning_rate": 1.478e-05, |
| "loss": 6.6373, |
| "mean_token_accuracy": 0.8748365368694067, |
| "num_tokens": 27711556.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 0.41494241636246443, |
| "epoch": 1.3439999999999999, |
| "grad_norm": 40.75, |
| "learning_rate": 1.475777777777778e-05, |
| "loss": 6.6603, |
| "mean_token_accuracy": 0.8731846924871206, |
| "num_tokens": 27795568.0, |
| "step": 3360 |
| }, |
| { |
| "entropy": 0.4036995633505285, |
| "epoch": 1.3479999999999999, |
| "grad_norm": 41.25, |
| "learning_rate": 1.4735555555555556e-05, |
| "loss": 6.3684, |
| "mean_token_accuracy": 0.8784338608384132, |
| "num_tokens": 27877049.0, |
| "step": 3370 |
| }, |
| { |
| "entropy": 0.39675605152733623, |
| "epoch": 1.3519999999999999, |
| "grad_norm": 41.75, |
| "learning_rate": 1.4713333333333335e-05, |
| "loss": 6.492, |
| "mean_token_accuracy": 0.8774603210389614, |
| "num_tokens": 27958162.0, |
| "step": 3380 |
| }, |
| { |
| "entropy": 0.40427405657246707, |
| "epoch": 1.3559999999999999, |
| "grad_norm": 53.0, |
| "learning_rate": 1.4691111111111111e-05, |
| "loss": 6.4467, |
| "mean_token_accuracy": 0.8750461477786302, |
| "num_tokens": 28040211.0, |
| "step": 3390 |
| }, |
| { |
| "entropy": 0.4059937232173979, |
| "epoch": 1.3599999999999999, |
| "grad_norm": 42.5, |
| "learning_rate": 1.466888888888889e-05, |
| "loss": 6.5553, |
| "mean_token_accuracy": 0.8755772355943918, |
| "num_tokens": 28129988.0, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "eval_chemistry_entropy": 0.5606725987792015, |
| "eval_chemistry_loss": 0.6744914054870605, |
| "eval_chemistry_mean_token_accuracy": 0.8119902350902557, |
| "eval_chemistry_num_tokens": 28129988.0, |
| "eval_chemistry_runtime": 53.6438, |
| "eval_chemistry_samples_per_second": 9.321, |
| "eval_chemistry_steps_per_second": 9.321, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "eval_physics_entropy": 0.5155527636408805, |
| "eval_physics_loss": 0.5951682925224304, |
| "eval_physics_mean_token_accuracy": 0.8287101131677628, |
| "eval_physics_num_tokens": 28129988.0, |
| "eval_physics_runtime": 62.3428, |
| "eval_physics_samples_per_second": 8.02, |
| "eval_physics_steps_per_second": 8.02, |
| "step": 3400 |
| }, |
| { |
| "entropy": 0.41343814926221967, |
| "epoch": 1.3639999999999999, |
| "grad_norm": 47.75, |
| "learning_rate": 1.4646666666666666e-05, |
| "loss": 6.6457, |
| "mean_token_accuracy": 0.8740956641733646, |
| "num_tokens": 28213255.0, |
| "step": 3410 |
| }, |
| { |
| "entropy": 0.40158893847838045, |
| "epoch": 1.3679999999999999, |
| "grad_norm": 47.0, |
| "learning_rate": 1.4624444444444446e-05, |
| "loss": 6.3413, |
| "mean_token_accuracy": 0.8786153614521026, |
| "num_tokens": 28299534.0, |
| "step": 3420 |
| }, |
| { |
| "entropy": 0.40043277870863675, |
| "epoch": 1.3719999999999999, |
| "grad_norm": 42.5, |
| "learning_rate": 1.4602222222222225e-05, |
| "loss": 6.4509, |
| "mean_token_accuracy": 0.8763358425348997, |
| "num_tokens": 28380294.0, |
| "step": 3430 |
| }, |
| { |
| "entropy": 0.40434538712725043, |
| "epoch": 1.376, |
| "grad_norm": 45.5, |
| "learning_rate": 1.4580000000000001e-05, |
| "loss": 6.4532, |
| "mean_token_accuracy": 0.8767665542662144, |
| "num_tokens": 28465903.0, |
| "step": 3440 |
| }, |
| { |
| "entropy": 0.40466274144127967, |
| "epoch": 1.38, |
| "grad_norm": 44.75, |
| "learning_rate": 1.455777777777778e-05, |
| "loss": 6.6484, |
| "mean_token_accuracy": 0.8732611689716577, |
| "num_tokens": 28551632.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 0.3937113340944052, |
| "epoch": 1.384, |
| "grad_norm": 52.75, |
| "learning_rate": 1.4535555555555556e-05, |
| "loss": 6.3348, |
| "mean_token_accuracy": 0.8784506808966398, |
| "num_tokens": 28639289.0, |
| "step": 3460 |
| }, |
| { |
| "entropy": 0.37205489771440625, |
| "epoch": 1.388, |
| "grad_norm": 39.5, |
| "learning_rate": 1.4513333333333336e-05, |
| "loss": 6.0176, |
| "mean_token_accuracy": 0.8824555825442075, |
| "num_tokens": 28718836.0, |
| "step": 3470 |
| }, |
| { |
| "entropy": 0.3729272528551519, |
| "epoch": 1.392, |
| "grad_norm": 61.75, |
| "learning_rate": 1.4491111111111111e-05, |
| "loss": 6.0158, |
| "mean_token_accuracy": 0.8861456740647554, |
| "num_tokens": 28801554.0, |
| "step": 3480 |
| }, |
| { |
| "entropy": 0.3962272494100034, |
| "epoch": 1.396, |
| "grad_norm": 45.25, |
| "learning_rate": 1.446888888888889e-05, |
| "loss": 6.415, |
| "mean_token_accuracy": 0.8784573219716549, |
| "num_tokens": 28880616.0, |
| "step": 3490 |
| }, |
| { |
| "entropy": 0.3926007304340601, |
| "epoch": 1.4, |
| "grad_norm": 42.75, |
| "learning_rate": 1.4446666666666668e-05, |
| "loss": 6.2795, |
| "mean_token_accuracy": 0.8782020095735789, |
| "num_tokens": 28963885.0, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_chemistry_entropy": 0.5384700215160847, |
| "eval_chemistry_loss": 0.6786037683486938, |
| "eval_chemistry_mean_token_accuracy": 0.8117350234985351, |
| "eval_chemistry_num_tokens": 28963885.0, |
| "eval_chemistry_runtime": 53.6924, |
| "eval_chemistry_samples_per_second": 9.312, |
| "eval_chemistry_steps_per_second": 9.312, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_physics_entropy": 0.4976633660644293, |
| "eval_physics_loss": 0.5983567833900452, |
| "eval_physics_mean_token_accuracy": 0.8291077345609665, |
| "eval_physics_num_tokens": 28963885.0, |
| "eval_physics_runtime": 62.5254, |
| "eval_physics_samples_per_second": 7.997, |
| "eval_physics_steps_per_second": 7.997, |
| "step": 3500 |
| }, |
| { |
| "entropy": 0.43768466394394634, |
| "epoch": 1.404, |
| "grad_norm": 41.25, |
| "learning_rate": 1.4424444444444446e-05, |
| "loss": 7.0969, |
| "mean_token_accuracy": 0.8666778188198805, |
| "num_tokens": 29044917.0, |
| "step": 3510 |
| }, |
| { |
| "entropy": 0.39439385654404757, |
| "epoch": 1.408, |
| "grad_norm": 45.0, |
| "learning_rate": 1.4402222222222224e-05, |
| "loss": 6.2961, |
| "mean_token_accuracy": 0.8791340485215187, |
| "num_tokens": 29125114.0, |
| "step": 3520 |
| }, |
| { |
| "entropy": 0.417308490537107, |
| "epoch": 1.412, |
| "grad_norm": 45.75, |
| "learning_rate": 1.4380000000000001e-05, |
| "loss": 6.7262, |
| "mean_token_accuracy": 0.8723568994551897, |
| "num_tokens": 29205761.0, |
| "step": 3530 |
| }, |
| { |
| "entropy": 0.44801882533356546, |
| "epoch": 1.416, |
| "grad_norm": 51.75, |
| "learning_rate": 1.4357777777777779e-05, |
| "loss": 7.2488, |
| "mean_token_accuracy": 0.8641116410493851, |
| "num_tokens": 29285272.0, |
| "step": 3540 |
| }, |
| { |
| "entropy": 0.40163839077576996, |
| "epoch": 1.42, |
| "grad_norm": 45.0, |
| "learning_rate": 1.4335555555555556e-05, |
| "loss": 6.4598, |
| "mean_token_accuracy": 0.8771747525781393, |
| "num_tokens": 29370113.0, |
| "step": 3550 |
| }, |
| { |
| "entropy": 0.4159936495125294, |
| "epoch": 1.424, |
| "grad_norm": 39.0, |
| "learning_rate": 1.4313333333333334e-05, |
| "loss": 6.6871, |
| "mean_token_accuracy": 0.8722648743540049, |
| "num_tokens": 29454334.0, |
| "step": 3560 |
| }, |
| { |
| "entropy": 0.40116758705116806, |
| "epoch": 1.428, |
| "grad_norm": 50.5, |
| "learning_rate": 1.4291111111111113e-05, |
| "loss": 6.2968, |
| "mean_token_accuracy": 0.87912851087749, |
| "num_tokens": 29531227.0, |
| "step": 3570 |
| }, |
| { |
| "entropy": 0.39880895167589187, |
| "epoch": 1.432, |
| "grad_norm": 37.25, |
| "learning_rate": 1.426888888888889e-05, |
| "loss": 6.4627, |
| "mean_token_accuracy": 0.8770294614136219, |
| "num_tokens": 29616865.0, |
| "step": 3580 |
| }, |
| { |
| "entropy": 0.40523217897862196, |
| "epoch": 1.436, |
| "grad_norm": 52.5, |
| "learning_rate": 1.4246666666666669e-05, |
| "loss": 6.5345, |
| "mean_token_accuracy": 0.8740318398922682, |
| "num_tokens": 29700797.0, |
| "step": 3590 |
| }, |
| { |
| "entropy": 0.4052128647454083, |
| "epoch": 1.44, |
| "grad_norm": 42.5, |
| "learning_rate": 1.4224444444444445e-05, |
| "loss": 6.4769, |
| "mean_token_accuracy": 0.8760498870164156, |
| "num_tokens": 29789253.0, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_chemistry_entropy": 0.5394897739291191, |
| "eval_chemistry_loss": 0.6791832447052002, |
| "eval_chemistry_mean_token_accuracy": 0.8112371909618378, |
| "eval_chemistry_num_tokens": 29789253.0, |
| "eval_chemistry_runtime": 53.648, |
| "eval_chemistry_samples_per_second": 9.32, |
| "eval_chemistry_steps_per_second": 9.32, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_physics_entropy": 0.4982254881858826, |
| "eval_physics_loss": 0.5965704321861267, |
| "eval_physics_mean_token_accuracy": 0.8296631572246551, |
| "eval_physics_num_tokens": 29789253.0, |
| "eval_physics_runtime": 62.3705, |
| "eval_physics_samples_per_second": 8.017, |
| "eval_physics_steps_per_second": 8.017, |
| "step": 3600 |
| }, |
| { |
| "entropy": 0.393766185734421, |
| "epoch": 1.444, |
| "grad_norm": 42.0, |
| "learning_rate": 1.4202222222222224e-05, |
| "loss": 6.4706, |
| "mean_token_accuracy": 0.8774504791945219, |
| "num_tokens": 29868398.0, |
| "step": 3610 |
| }, |
| { |
| "entropy": 0.41584292319603267, |
| "epoch": 1.448, |
| "grad_norm": 46.5, |
| "learning_rate": 1.418e-05, |
| "loss": 6.6261, |
| "mean_token_accuracy": 0.8746451210230589, |
| "num_tokens": 29953006.0, |
| "step": 3620 |
| }, |
| { |
| "entropy": 0.3903368269558996, |
| "epoch": 1.452, |
| "grad_norm": 51.75, |
| "learning_rate": 1.4157777777777779e-05, |
| "loss": 6.3795, |
| "mean_token_accuracy": 0.8790011119097472, |
| "num_tokens": 30038607.0, |
| "step": 3630 |
| }, |
| { |
| "entropy": 0.39744718382135036, |
| "epoch": 1.456, |
| "grad_norm": 41.75, |
| "learning_rate": 1.4135555555555555e-05, |
| "loss": 6.2495, |
| "mean_token_accuracy": 0.8795612748712301, |
| "num_tokens": 30128576.0, |
| "step": 3640 |
| }, |
| { |
| "entropy": 0.40468403697013855, |
| "epoch": 1.46, |
| "grad_norm": 45.25, |
| "learning_rate": 1.4113333333333334e-05, |
| "loss": 6.7435, |
| "mean_token_accuracy": 0.8736757151782513, |
| "num_tokens": 30210823.0, |
| "step": 3650 |
| }, |
| { |
| "entropy": 0.4109737670980394, |
| "epoch": 1.464, |
| "grad_norm": 46.75, |
| "learning_rate": 1.4091111111111114e-05, |
| "loss": 6.3109, |
| "mean_token_accuracy": 0.8789023902267218, |
| "num_tokens": 30288894.0, |
| "step": 3660 |
| }, |
| { |
| "entropy": 0.4134160808287561, |
| "epoch": 1.468, |
| "grad_norm": 52.25, |
| "learning_rate": 1.406888888888889e-05, |
| "loss": 6.8543, |
| "mean_token_accuracy": 0.8711716037243604, |
| "num_tokens": 30367689.0, |
| "step": 3670 |
| }, |
| { |
| "entropy": 0.4443310149013996, |
| "epoch": 1.472, |
| "grad_norm": 48.25, |
| "learning_rate": 1.4046666666666669e-05, |
| "loss": 6.9875, |
| "mean_token_accuracy": 0.8682264130562544, |
| "num_tokens": 30452719.0, |
| "step": 3680 |
| }, |
| { |
| "entropy": 0.3913025620393455, |
| "epoch": 1.476, |
| "grad_norm": 43.0, |
| "learning_rate": 1.4024444444444445e-05, |
| "loss": 6.268, |
| "mean_token_accuracy": 0.8797603964805603, |
| "num_tokens": 30536190.0, |
| "step": 3690 |
| }, |
| { |
| "entropy": 0.3860092952847481, |
| "epoch": 1.48, |
| "grad_norm": 41.5, |
| "learning_rate": 1.4002222222222224e-05, |
| "loss": 6.3353, |
| "mean_token_accuracy": 0.8799397245049476, |
| "num_tokens": 30620659.0, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.48, |
| "eval_chemistry_entropy": 0.5516593392193317, |
| "eval_chemistry_loss": 0.6761385202407837, |
| "eval_chemistry_mean_token_accuracy": 0.8124918038845063, |
| "eval_chemistry_num_tokens": 30620659.0, |
| "eval_chemistry_runtime": 54.0653, |
| "eval_chemistry_samples_per_second": 9.248, |
| "eval_chemistry_steps_per_second": 9.248, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.48, |
| "eval_physics_entropy": 0.5061543031334877, |
| "eval_physics_loss": 0.5945616364479065, |
| "eval_physics_mean_token_accuracy": 0.8298771587014199, |
| "eval_physics_num_tokens": 30620659.0, |
| "eval_physics_runtime": 62.705, |
| "eval_physics_samples_per_second": 7.974, |
| "eval_physics_steps_per_second": 7.974, |
| "step": 3700 |
| }, |
| { |
| "entropy": 0.4068119526375085, |
| "epoch": 1.484, |
| "grad_norm": 39.75, |
| "learning_rate": 1.398e-05, |
| "loss": 6.3487, |
| "mean_token_accuracy": 0.8779210794717074, |
| "num_tokens": 30700777.0, |
| "step": 3710 |
| }, |
| { |
| "entropy": 0.3898567968979478, |
| "epoch": 1.488, |
| "grad_norm": 90.5, |
| "learning_rate": 1.395777777777778e-05, |
| "loss": 6.3799, |
| "mean_token_accuracy": 0.8781911455094814, |
| "num_tokens": 30782343.0, |
| "step": 3720 |
| }, |
| { |
| "entropy": 0.4058146263472736, |
| "epoch": 1.492, |
| "grad_norm": 56.0, |
| "learning_rate": 1.3935555555555557e-05, |
| "loss": 6.4268, |
| "mean_token_accuracy": 0.8762706536799669, |
| "num_tokens": 30867783.0, |
| "step": 3730 |
| }, |
| { |
| "entropy": 0.3867638412863016, |
| "epoch": 1.496, |
| "grad_norm": 50.5, |
| "learning_rate": 1.3913333333333335e-05, |
| "loss": 6.3126, |
| "mean_token_accuracy": 0.8784434229135514, |
| "num_tokens": 30947703.0, |
| "step": 3740 |
| }, |
| { |
| "entropy": 0.41046067867428065, |
| "epoch": 1.5, |
| "grad_norm": 49.25, |
| "learning_rate": 1.3891111111111114e-05, |
| "loss": 6.6858, |
| "mean_token_accuracy": 0.8727071076631546, |
| "num_tokens": 31029847.0, |
| "step": 3750 |
| }, |
| { |
| "entropy": 0.3890328987501562, |
| "epoch": 1.504, |
| "grad_norm": 48.75, |
| "learning_rate": 1.386888888888889e-05, |
| "loss": 6.1404, |
| "mean_token_accuracy": 0.8820106990635395, |
| "num_tokens": 31113238.0, |
| "step": 3760 |
| }, |
| { |
| "entropy": 0.4187105460092425, |
| "epoch": 1.508, |
| "grad_norm": 37.5, |
| "learning_rate": 1.3846666666666669e-05, |
| "loss": 6.7747, |
| "mean_token_accuracy": 0.872544726729393, |
| "num_tokens": 31198778.0, |
| "step": 3770 |
| }, |
| { |
| "entropy": 0.4151353104971349, |
| "epoch": 1.512, |
| "grad_norm": 37.5, |
| "learning_rate": 1.3824444444444445e-05, |
| "loss": 6.7056, |
| "mean_token_accuracy": 0.871716808527708, |
| "num_tokens": 31283883.0, |
| "step": 3780 |
| }, |
| { |
| "entropy": 0.4268311742693186, |
| "epoch": 1.516, |
| "grad_norm": 45.25, |
| "learning_rate": 1.3802222222222224e-05, |
| "loss": 6.8163, |
| "mean_token_accuracy": 0.8693723428994418, |
| "num_tokens": 31363764.0, |
| "step": 3790 |
| }, |
| { |
| "entropy": 0.4101722952444106, |
| "epoch": 1.52, |
| "grad_norm": 53.75, |
| "learning_rate": 1.378e-05, |
| "loss": 6.5721, |
| "mean_token_accuracy": 0.8730484273284673, |
| "num_tokens": 31444589.0, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.52, |
| "eval_chemistry_entropy": 0.5600586042702198, |
| "eval_chemistry_loss": 0.6745473742485046, |
| "eval_chemistry_mean_token_accuracy": 0.8113394799232483, |
| "eval_chemistry_num_tokens": 31444589.0, |
| "eval_chemistry_runtime": 53.5558, |
| "eval_chemistry_samples_per_second": 9.336, |
| "eval_chemistry_steps_per_second": 9.336, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.52, |
| "eval_physics_entropy": 0.5140104497522116, |
| "eval_physics_loss": 0.5923190116882324, |
| "eval_physics_mean_token_accuracy": 0.8303033008575439, |
| "eval_physics_num_tokens": 31444589.0, |
| "eval_physics_runtime": 64.0549, |
| "eval_physics_samples_per_second": 7.806, |
| "eval_physics_steps_per_second": 7.806, |
| "step": 3800 |
| }, |
| { |
| "entropy": 0.3989151350222528, |
| "epoch": 1.524, |
| "grad_norm": 38.5, |
| "learning_rate": 1.375777777777778e-05, |
| "loss": 6.3236, |
| "mean_token_accuracy": 0.8772641956806183, |
| "num_tokens": 31527312.0, |
| "step": 3810 |
| }, |
| { |
| "entropy": 0.3823771147057414, |
| "epoch": 1.528, |
| "grad_norm": 41.0, |
| "learning_rate": 1.3735555555555557e-05, |
| "loss": 6.2511, |
| "mean_token_accuracy": 0.880349512398243, |
| "num_tokens": 31608952.0, |
| "step": 3820 |
| }, |
| { |
| "entropy": 0.40338705498725175, |
| "epoch": 1.532, |
| "grad_norm": 47.0, |
| "learning_rate": 1.3713333333333335e-05, |
| "loss": 6.3916, |
| "mean_token_accuracy": 0.8770292654633522, |
| "num_tokens": 31689112.0, |
| "step": 3830 |
| }, |
| { |
| "entropy": 0.4159190553240478, |
| "epoch": 1.536, |
| "grad_norm": 52.75, |
| "learning_rate": 1.3691111111111112e-05, |
| "loss": 6.7008, |
| "mean_token_accuracy": 0.8723959777504205, |
| "num_tokens": 31774137.0, |
| "step": 3840 |
| }, |
| { |
| "entropy": 0.4056047718971968, |
| "epoch": 1.54, |
| "grad_norm": 53.5, |
| "learning_rate": 1.366888888888889e-05, |
| "loss": 6.5033, |
| "mean_token_accuracy": 0.874358582124114, |
| "num_tokens": 31855139.0, |
| "step": 3850 |
| }, |
| { |
| "entropy": 0.3725484909489751, |
| "epoch": 1.544, |
| "grad_norm": 50.25, |
| "learning_rate": 1.3646666666666668e-05, |
| "loss": 5.9503, |
| "mean_token_accuracy": 0.8854304205626249, |
| "num_tokens": 31937927.0, |
| "step": 3860 |
| }, |
| { |
| "entropy": 0.3921050449833274, |
| "epoch": 1.548, |
| "grad_norm": 42.25, |
| "learning_rate": 1.3624444444444445e-05, |
| "loss": 6.4555, |
| "mean_token_accuracy": 0.8776751708239316, |
| "num_tokens": 32020695.0, |
| "step": 3870 |
| }, |
| { |
| "entropy": 0.4078158959746361, |
| "epoch": 1.552, |
| "grad_norm": 39.25, |
| "learning_rate": 1.3602222222222223e-05, |
| "loss": 6.3901, |
| "mean_token_accuracy": 0.8780841447412968, |
| "num_tokens": 32101776.0, |
| "step": 3880 |
| }, |
| { |
| "entropy": 0.38753908928483727, |
| "epoch": 1.556, |
| "grad_norm": 43.5, |
| "learning_rate": 1.3580000000000002e-05, |
| "loss": 6.2953, |
| "mean_token_accuracy": 0.878034945949912, |
| "num_tokens": 32186113.0, |
| "step": 3890 |
| }, |
| { |
| "entropy": 0.39779740227386357, |
| "epoch": 1.56, |
| "grad_norm": 45.5, |
| "learning_rate": 1.3557777777777778e-05, |
| "loss": 6.3673, |
| "mean_token_accuracy": 0.8784384347498417, |
| "num_tokens": 32271213.0, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.56, |
| "eval_chemistry_entropy": 0.5504012902975083, |
| "eval_chemistry_loss": 0.6732741594314575, |
| "eval_chemistry_mean_token_accuracy": 0.8128898606300354, |
| "eval_chemistry_num_tokens": 32271213.0, |
| "eval_chemistry_runtime": 53.7613, |
| "eval_chemistry_samples_per_second": 9.3, |
| "eval_chemistry_steps_per_second": 9.3, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.56, |
| "eval_physics_entropy": 0.5060150835365057, |
| "eval_physics_loss": 0.5907258987426758, |
| "eval_physics_mean_token_accuracy": 0.8303489559888839, |
| "eval_physics_num_tokens": 32271213.0, |
| "eval_physics_runtime": 62.2781, |
| "eval_physics_samples_per_second": 8.028, |
| "eval_physics_steps_per_second": 8.028, |
| "step": 3900 |
| }, |
| { |
| "entropy": 0.39733350006863477, |
| "epoch": 1.564, |
| "grad_norm": 47.25, |
| "learning_rate": 1.3535555555555557e-05, |
| "loss": 6.4008, |
| "mean_token_accuracy": 0.8777061901986599, |
| "num_tokens": 32348533.0, |
| "step": 3910 |
| }, |
| { |
| "entropy": 0.3997656940482557, |
| "epoch": 1.568, |
| "grad_norm": 46.75, |
| "learning_rate": 1.3513333333333333e-05, |
| "loss": 6.4498, |
| "mean_token_accuracy": 0.8779531549662352, |
| "num_tokens": 32428021.0, |
| "step": 3920 |
| }, |
| { |
| "entropy": 0.3962811196222901, |
| "epoch": 1.572, |
| "grad_norm": 43.25, |
| "learning_rate": 1.3491111111111113e-05, |
| "loss": 6.426, |
| "mean_token_accuracy": 0.8753586910665035, |
| "num_tokens": 32507699.0, |
| "step": 3930 |
| }, |
| { |
| "entropy": 0.4098018233664334, |
| "epoch": 1.576, |
| "grad_norm": 46.0, |
| "learning_rate": 1.3468888888888888e-05, |
| "loss": 6.4576, |
| "mean_token_accuracy": 0.8761188194155693, |
| "num_tokens": 32585407.0, |
| "step": 3940 |
| }, |
| { |
| "entropy": 0.41058400813490153, |
| "epoch": 1.58, |
| "grad_norm": 44.5, |
| "learning_rate": 1.3446666666666668e-05, |
| "loss": 6.7808, |
| "mean_token_accuracy": 0.8717385150492192, |
| "num_tokens": 32670428.0, |
| "step": 3950 |
| }, |
| { |
| "entropy": 0.39778603641316296, |
| "epoch": 1.584, |
| "grad_norm": 52.25, |
| "learning_rate": 1.3424444444444447e-05, |
| "loss": 6.3636, |
| "mean_token_accuracy": 0.8788483895361423, |
| "num_tokens": 32752735.0, |
| "step": 3960 |
| }, |
| { |
| "entropy": 0.38312863996252416, |
| "epoch": 1.588, |
| "grad_norm": 43.0, |
| "learning_rate": 1.3402222222222223e-05, |
| "loss": 6.086, |
| "mean_token_accuracy": 0.8815972603857517, |
| "num_tokens": 32831548.0, |
| "step": 3970 |
| }, |
| { |
| "entropy": 0.39520974569022654, |
| "epoch": 1.592, |
| "grad_norm": 40.75, |
| "learning_rate": 1.3380000000000002e-05, |
| "loss": 6.3631, |
| "mean_token_accuracy": 0.878123789280653, |
| "num_tokens": 32912519.0, |
| "step": 3980 |
| }, |
| { |
| "entropy": 0.3998935830779374, |
| "epoch": 1.596, |
| "grad_norm": 49.0, |
| "learning_rate": 1.3357777777777778e-05, |
| "loss": 6.4147, |
| "mean_token_accuracy": 0.8768809117376805, |
| "num_tokens": 32993186.0, |
| "step": 3990 |
| }, |
| { |
| "entropy": 0.3972979296930134, |
| "epoch": 1.6, |
| "grad_norm": 38.5, |
| "learning_rate": 1.3335555555555558e-05, |
| "loss": 6.3371, |
| "mean_token_accuracy": 0.879148568585515, |
| "num_tokens": 33075822.0, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_chemistry_entropy": 0.5355219095349312, |
| "eval_chemistry_loss": 0.6751107573509216, |
| "eval_chemistry_mean_token_accuracy": 0.8136024585962296, |
| "eval_chemistry_num_tokens": 33075822.0, |
| "eval_chemistry_runtime": 53.4912, |
| "eval_chemistry_samples_per_second": 9.347, |
| "eval_chemistry_steps_per_second": 9.347, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_physics_entropy": 0.4959153833836317, |
| "eval_physics_loss": 0.5912042856216431, |
| "eval_physics_mean_token_accuracy": 0.8305088123679161, |
| "eval_physics_num_tokens": 33075822.0, |
| "eval_physics_runtime": 62.2699, |
| "eval_physics_samples_per_second": 8.03, |
| "eval_physics_steps_per_second": 8.03, |
| "step": 4000 |
| }, |
| { |
| "entropy": 0.38236242197453973, |
| "epoch": 1.604, |
| "grad_norm": 40.5, |
| "learning_rate": 1.3313333333333333e-05, |
| "loss": 6.115, |
| "mean_token_accuracy": 0.8812222603708506, |
| "num_tokens": 33160214.0, |
| "step": 4010 |
| }, |
| { |
| "entropy": 0.3806236485484987, |
| "epoch": 1.608, |
| "grad_norm": 52.25, |
| "learning_rate": 1.3291111111111113e-05, |
| "loss": 6.1912, |
| "mean_token_accuracy": 0.8828809015452862, |
| "num_tokens": 33250394.0, |
| "step": 4020 |
| }, |
| { |
| "entropy": 0.3983167938888073, |
| "epoch": 1.612, |
| "grad_norm": 44.5, |
| "learning_rate": 1.3268888888888889e-05, |
| "loss": 6.4582, |
| "mean_token_accuracy": 0.877009741216898, |
| "num_tokens": 33332517.0, |
| "step": 4030 |
| }, |
| { |
| "entropy": 0.4042822897899896, |
| "epoch": 1.616, |
| "grad_norm": 40.0, |
| "learning_rate": 1.3246666666666668e-05, |
| "loss": 6.4116, |
| "mean_token_accuracy": 0.8771112740039826, |
| "num_tokens": 33411850.0, |
| "step": 4040 |
| }, |
| { |
| "entropy": 0.3686965470202267, |
| "epoch": 1.62, |
| "grad_norm": 45.75, |
| "learning_rate": 1.3224444444444446e-05, |
| "loss": 5.968, |
| "mean_token_accuracy": 0.884541454911232, |
| "num_tokens": 33496033.0, |
| "step": 4050 |
| }, |
| { |
| "entropy": 0.38407273441553114, |
| "epoch": 1.624, |
| "grad_norm": 36.5, |
| "learning_rate": 1.3202222222222223e-05, |
| "loss": 6.3121, |
| "mean_token_accuracy": 0.8793533518910408, |
| "num_tokens": 33577978.0, |
| "step": 4060 |
| }, |
| { |
| "entropy": 0.41591387512162326, |
| "epoch": 1.6280000000000001, |
| "grad_norm": 45.5, |
| "learning_rate": 1.3180000000000001e-05, |
| "loss": 6.5055, |
| "mean_token_accuracy": 0.8755687132477761, |
| "num_tokens": 33658837.0, |
| "step": 4070 |
| }, |
| { |
| "entropy": 0.3909124245867133, |
| "epoch": 1.6320000000000001, |
| "grad_norm": 53.25, |
| "learning_rate": 1.3157777777777778e-05, |
| "loss": 6.4706, |
| "mean_token_accuracy": 0.874223543331027, |
| "num_tokens": 33739456.0, |
| "step": 4080 |
| }, |
| { |
| "entropy": 0.3910256386734545, |
| "epoch": 1.6360000000000001, |
| "grad_norm": 44.5, |
| "learning_rate": 1.3135555555555558e-05, |
| "loss": 6.1275, |
| "mean_token_accuracy": 0.8816055655479431, |
| "num_tokens": 33824629.0, |
| "step": 4090 |
| }, |
| { |
| "entropy": 0.3737372735515237, |
| "epoch": 1.6400000000000001, |
| "grad_norm": 40.75, |
| "learning_rate": 1.3113333333333334e-05, |
| "loss": 6.0599, |
| "mean_token_accuracy": 0.8833718582987785, |
| "num_tokens": 33904537.0, |
| "step": 4100 |
| }, |
| { |
| "epoch": 1.6400000000000001, |
| "eval_chemistry_entropy": 0.5424275600910187, |
| "eval_chemistry_loss": 0.6766899228096008, |
| "eval_chemistry_mean_token_accuracy": 0.8130618922114372, |
| "eval_chemistry_num_tokens": 33904537.0, |
| "eval_chemistry_runtime": 53.8198, |
| "eval_chemistry_samples_per_second": 9.29, |
| "eval_chemistry_steps_per_second": 9.29, |
| "step": 4100 |
| }, |
| { |
| "epoch": 1.6400000000000001, |
| "eval_physics_entropy": 0.49989713841676714, |
| "eval_physics_loss": 0.5913661122322083, |
| "eval_physics_mean_token_accuracy": 0.8308604298830032, |
| "eval_physics_num_tokens": 33904537.0, |
| "eval_physics_runtime": 62.549, |
| "eval_physics_samples_per_second": 7.994, |
| "eval_physics_steps_per_second": 7.994, |
| "step": 4100 |
| }, |
| { |
| "entropy": 0.3754084711894393, |
| "epoch": 1.6440000000000001, |
| "grad_norm": 49.0, |
| "learning_rate": 1.3091111111111113e-05, |
| "loss": 5.9604, |
| "mean_token_accuracy": 0.8852428376674653, |
| "num_tokens": 33987737.0, |
| "step": 4110 |
| }, |
| { |
| "entropy": 0.3802527576684952, |
| "epoch": 1.6480000000000001, |
| "grad_norm": 46.5, |
| "learning_rate": 1.306888888888889e-05, |
| "loss": 6.0927, |
| "mean_token_accuracy": 0.8817774288356304, |
| "num_tokens": 34072022.0, |
| "step": 4120 |
| }, |
| { |
| "entropy": 0.3913967923261225, |
| "epoch": 1.6520000000000001, |
| "grad_norm": 40.5, |
| "learning_rate": 1.3046666666666668e-05, |
| "loss": 6.4194, |
| "mean_token_accuracy": 0.8791510999202728, |
| "num_tokens": 34154187.0, |
| "step": 4130 |
| }, |
| { |
| "entropy": 0.40655491799116134, |
| "epoch": 1.6560000000000001, |
| "grad_norm": 45.0, |
| "learning_rate": 1.3024444444444446e-05, |
| "loss": 6.5256, |
| "mean_token_accuracy": 0.8768716558814049, |
| "num_tokens": 34236954.0, |
| "step": 4140 |
| }, |
| { |
| "entropy": 0.396803954988718, |
| "epoch": 1.6600000000000001, |
| "grad_norm": 43.5, |
| "learning_rate": 1.3002222222222223e-05, |
| "loss": 6.2763, |
| "mean_token_accuracy": 0.8783984709531069, |
| "num_tokens": 34323386.0, |
| "step": 4150 |
| }, |
| { |
| "entropy": 0.39772137328982354, |
| "epoch": 1.6640000000000001, |
| "grad_norm": 50.75, |
| "learning_rate": 1.2980000000000001e-05, |
| "loss": 6.5304, |
| "mean_token_accuracy": 0.8762561745941639, |
| "num_tokens": 34398959.0, |
| "step": 4160 |
| }, |
| { |
| "entropy": 0.395791903976351, |
| "epoch": 1.6680000000000001, |
| "grad_norm": 52.0, |
| "learning_rate": 1.2957777777777779e-05, |
| "loss": 6.3265, |
| "mean_token_accuracy": 0.87955605648458, |
| "num_tokens": 34477272.0, |
| "step": 4170 |
| }, |
| { |
| "entropy": 0.37107134936377406, |
| "epoch": 1.6720000000000002, |
| "grad_norm": 40.0, |
| "learning_rate": 1.2935555555555556e-05, |
| "loss": 5.933, |
| "mean_token_accuracy": 0.8845330536365509, |
| "num_tokens": 34564364.0, |
| "step": 4180 |
| }, |
| { |
| "entropy": 0.3933924556709826, |
| "epoch": 1.6760000000000002, |
| "grad_norm": 42.0, |
| "learning_rate": 1.2913333333333336e-05, |
| "loss": 6.424, |
| "mean_token_accuracy": 0.8781571734696627, |
| "num_tokens": 34649149.0, |
| "step": 4190 |
| }, |
| { |
| "entropy": 0.41130870999768376, |
| "epoch": 1.6800000000000002, |
| "grad_norm": 48.25, |
| "learning_rate": 1.2891111111111112e-05, |
| "loss": 6.5347, |
| "mean_token_accuracy": 0.8747550565749407, |
| "num_tokens": 34732284.0, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "eval_chemistry_entropy": 0.5510465578138828, |
| "eval_chemistry_loss": 0.6722443699836731, |
| "eval_chemistry_mean_token_accuracy": 0.8126014887094498, |
| "eval_chemistry_num_tokens": 34732284.0, |
| "eval_chemistry_runtime": 53.7812, |
| "eval_chemistry_samples_per_second": 9.297, |
| "eval_chemistry_steps_per_second": 9.297, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "eval_physics_entropy": 0.5065301542282105, |
| "eval_physics_loss": 0.588254988193512, |
| "eval_physics_mean_token_accuracy": 0.8313609339594841, |
| "eval_physics_num_tokens": 34732284.0, |
| "eval_physics_runtime": 62.4485, |
| "eval_physics_samples_per_second": 8.007, |
| "eval_physics_steps_per_second": 8.007, |
| "step": 4200 |
| }, |
| { |
| "entropy": 0.3890102437697351, |
| "epoch": 1.6840000000000002, |
| "grad_norm": 38.75, |
| "learning_rate": 1.2868888888888891e-05, |
| "loss": 6.2136, |
| "mean_token_accuracy": 0.8815694730728865, |
| "num_tokens": 34818032.0, |
| "step": 4210 |
| }, |
| { |
| "entropy": 0.3943379674106836, |
| "epoch": 1.688, |
| "grad_norm": 42.25, |
| "learning_rate": 1.2846666666666667e-05, |
| "loss": 6.5283, |
| "mean_token_accuracy": 0.8765201598405838, |
| "num_tokens": 34895374.0, |
| "step": 4220 |
| }, |
| { |
| "entropy": 0.4018792214803398, |
| "epoch": 1.692, |
| "grad_norm": 50.25, |
| "learning_rate": 1.2824444444444446e-05, |
| "loss": 6.4101, |
| "mean_token_accuracy": 0.8787004798650742, |
| "num_tokens": 34975789.0, |
| "step": 4230 |
| }, |
| { |
| "entropy": 0.4061967826448381, |
| "epoch": 1.696, |
| "grad_norm": 47.75, |
| "learning_rate": 1.2802222222222222e-05, |
| "loss": 6.5462, |
| "mean_token_accuracy": 0.8755400076508522, |
| "num_tokens": 35053712.0, |
| "step": 4240 |
| }, |
| { |
| "entropy": 0.40665144557133315, |
| "epoch": 1.7, |
| "grad_norm": 47.5, |
| "learning_rate": 1.2780000000000001e-05, |
| "loss": 6.4962, |
| "mean_token_accuracy": 0.8734507616609335, |
| "num_tokens": 35133339.0, |
| "step": 4250 |
| }, |
| { |
| "entropy": 0.3985592287033796, |
| "epoch": 1.704, |
| "grad_norm": 47.5, |
| "learning_rate": 1.2757777777777777e-05, |
| "loss": 6.4644, |
| "mean_token_accuracy": 0.8761161752045155, |
| "num_tokens": 35216941.0, |
| "step": 4260 |
| }, |
| { |
| "entropy": 0.40054804934188726, |
| "epoch": 1.708, |
| "grad_norm": 46.0, |
| "learning_rate": 1.2735555555555557e-05, |
| "loss": 6.4884, |
| "mean_token_accuracy": 0.8772318150848151, |
| "num_tokens": 35305882.0, |
| "step": 4270 |
| }, |
| { |
| "entropy": 0.41109891440719365, |
| "epoch": 1.712, |
| "grad_norm": 41.25, |
| "learning_rate": 1.2713333333333336e-05, |
| "loss": 6.4997, |
| "mean_token_accuracy": 0.8744318414479494, |
| "num_tokens": 35393088.0, |
| "step": 4280 |
| }, |
| { |
| "entropy": 0.39241413585841656, |
| "epoch": 1.716, |
| "grad_norm": 51.0, |
| "learning_rate": 1.2691111111111112e-05, |
| "loss": 6.2986, |
| "mean_token_accuracy": 0.8791064377874136, |
| "num_tokens": 35475213.0, |
| "step": 4290 |
| }, |
| { |
| "entropy": 0.3878518451936543, |
| "epoch": 1.72, |
| "grad_norm": 43.75, |
| "learning_rate": 1.2668888888888891e-05, |
| "loss": 6.3365, |
| "mean_token_accuracy": 0.8789217792451381, |
| "num_tokens": 35559385.0, |
| "step": 4300 |
| }, |
| { |
| "epoch": 1.72, |
| "eval_chemistry_entropy": 0.5547326206564903, |
| "eval_chemistry_loss": 0.6720637679100037, |
| "eval_chemistry_mean_token_accuracy": 0.8123885672688484, |
| "eval_chemistry_num_tokens": 35559385.0, |
| "eval_chemistry_runtime": 53.7838, |
| "eval_chemistry_samples_per_second": 9.296, |
| "eval_chemistry_steps_per_second": 9.296, |
| "step": 4300 |
| }, |
| { |
| "epoch": 1.72, |
| "eval_physics_entropy": 0.5108413529396058, |
| "eval_physics_loss": 0.5859846472740173, |
| "eval_physics_mean_token_accuracy": 0.8304098455309867, |
| "eval_physics_num_tokens": 35559385.0, |
| "eval_physics_runtime": 62.5915, |
| "eval_physics_samples_per_second": 7.988, |
| "eval_physics_steps_per_second": 7.988, |
| "step": 4300 |
| }, |
| { |
| "entropy": 0.40798138780519366, |
| "epoch": 1.724, |
| "grad_norm": 57.75, |
| "learning_rate": 1.2646666666666667e-05, |
| "loss": 6.4559, |
| "mean_token_accuracy": 0.8757931537926197, |
| "num_tokens": 35641581.0, |
| "step": 4310 |
| }, |
| { |
| "entropy": 0.397324959281832, |
| "epoch": 1.728, |
| "grad_norm": 40.0, |
| "learning_rate": 1.2624444444444446e-05, |
| "loss": 6.4721, |
| "mean_token_accuracy": 0.8773955579847097, |
| "num_tokens": 35729007.0, |
| "step": 4320 |
| }, |
| { |
| "entropy": 0.39897064603865146, |
| "epoch": 1.732, |
| "grad_norm": 38.25, |
| "learning_rate": 1.2602222222222222e-05, |
| "loss": 6.3887, |
| "mean_token_accuracy": 0.8778614915907383, |
| "num_tokens": 35817187.0, |
| "step": 4330 |
| }, |
| { |
| "entropy": 0.38607349833473564, |
| "epoch": 1.736, |
| "grad_norm": 55.75, |
| "learning_rate": 1.2580000000000002e-05, |
| "loss": 6.3246, |
| "mean_token_accuracy": 0.8786908566951752, |
| "num_tokens": 35905199.0, |
| "step": 4340 |
| }, |
| { |
| "entropy": 0.4305374707095325, |
| "epoch": 1.74, |
| "grad_norm": 42.75, |
| "learning_rate": 1.2557777777777779e-05, |
| "loss": 6.865, |
| "mean_token_accuracy": 0.8699071381241084, |
| "num_tokens": 35987415.0, |
| "step": 4350 |
| }, |
| { |
| "entropy": 0.40012558540329335, |
| "epoch": 1.744, |
| "grad_norm": 47.0, |
| "learning_rate": 1.2535555555555557e-05, |
| "loss": 6.4054, |
| "mean_token_accuracy": 0.879029955342412, |
| "num_tokens": 36072489.0, |
| "step": 4360 |
| }, |
| { |
| "entropy": 0.3851448309607804, |
| "epoch": 1.748, |
| "grad_norm": 42.75, |
| "learning_rate": 1.2513333333333334e-05, |
| "loss": 6.3061, |
| "mean_token_accuracy": 0.8798547301441431, |
| "num_tokens": 36157560.0, |
| "step": 4370 |
| }, |
| { |
| "entropy": 0.39314311477355657, |
| "epoch": 1.752, |
| "grad_norm": 46.75, |
| "learning_rate": 1.2491111111111112e-05, |
| "loss": 6.2799, |
| "mean_token_accuracy": 0.8792950961738825, |
| "num_tokens": 36240600.0, |
| "step": 4380 |
| }, |
| { |
| "entropy": 0.3847956730984151, |
| "epoch": 1.756, |
| "grad_norm": 45.0, |
| "learning_rate": 1.246888888888889e-05, |
| "loss": 6.114, |
| "mean_token_accuracy": 0.8813075732439757, |
| "num_tokens": 36318165.0, |
| "step": 4390 |
| }, |
| { |
| "entropy": 0.3810992536135018, |
| "epoch": 1.76, |
| "grad_norm": 43.0, |
| "learning_rate": 1.2446666666666667e-05, |
| "loss": 6.1448, |
| "mean_token_accuracy": 0.8820089619606734, |
| "num_tokens": 36398285.0, |
| "step": 4400 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_chemistry_entropy": 0.5499019548296928, |
| "eval_chemistry_loss": 0.6719583868980408, |
| "eval_chemistry_mean_token_accuracy": 0.8134790292978287, |
| "eval_chemistry_num_tokens": 36398285.0, |
| "eval_chemistry_runtime": 53.5144, |
| "eval_chemistry_samples_per_second": 9.343, |
| "eval_chemistry_steps_per_second": 9.343, |
| "step": 4400 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_physics_entropy": 0.5046378436386585, |
| "eval_physics_loss": 0.5862331390380859, |
| "eval_physics_mean_token_accuracy": 0.8315197025537491, |
| "eval_physics_num_tokens": 36398285.0, |
| "eval_physics_runtime": 66.0295, |
| "eval_physics_samples_per_second": 7.572, |
| "eval_physics_steps_per_second": 7.572, |
| "step": 4400 |
| }, |
| { |
| "entropy": 0.414799137134105, |
| "epoch": 1.764, |
| "grad_norm": 49.0, |
| "learning_rate": 1.2424444444444445e-05, |
| "loss": 6.6864, |
| "mean_token_accuracy": 0.8711853481829166, |
| "num_tokens": 36478465.0, |
| "step": 4410 |
| }, |
| { |
| "entropy": 0.39798269486054777, |
| "epoch": 1.768, |
| "grad_norm": 46.75, |
| "learning_rate": 1.2402222222222222e-05, |
| "loss": 6.3449, |
| "mean_token_accuracy": 0.8790823489427566, |
| "num_tokens": 36559891.0, |
| "step": 4420 |
| }, |
| { |
| "entropy": 0.39331792537122967, |
| "epoch": 1.772, |
| "grad_norm": 37.25, |
| "learning_rate": 1.2380000000000002e-05, |
| "loss": 6.3936, |
| "mean_token_accuracy": 0.8780659079551697, |
| "num_tokens": 36645714.0, |
| "step": 4430 |
| }, |
| { |
| "entropy": 0.3999379160813987, |
| "epoch": 1.776, |
| "grad_norm": 43.0, |
| "learning_rate": 1.235777777777778e-05, |
| "loss": 6.4141, |
| "mean_token_accuracy": 0.8769634023308754, |
| "num_tokens": 36730479.0, |
| "step": 4440 |
| }, |
| { |
| "entropy": 0.39414182072505355, |
| "epoch": 1.78, |
| "grad_norm": 45.5, |
| "learning_rate": 1.2335555555555557e-05, |
| "loss": 6.3443, |
| "mean_token_accuracy": 0.8797257397323847, |
| "num_tokens": 36812010.0, |
| "step": 4450 |
| }, |
| { |
| "entropy": 0.37193125137127936, |
| "epoch": 1.784, |
| "grad_norm": 42.25, |
| "learning_rate": 1.2313333333333335e-05, |
| "loss": 5.9259, |
| "mean_token_accuracy": 0.8858068864792585, |
| "num_tokens": 36897454.0, |
| "step": 4460 |
| }, |
| { |
| "entropy": 0.41305548381060364, |
| "epoch": 1.788, |
| "grad_norm": 45.5, |
| "learning_rate": 1.2291111111111112e-05, |
| "loss": 6.668, |
| "mean_token_accuracy": 0.8740019179880619, |
| "num_tokens": 36977906.0, |
| "step": 4470 |
| }, |
| { |
| "entropy": 0.40217553824186325, |
| "epoch": 1.792, |
| "grad_norm": 56.75, |
| "learning_rate": 1.226888888888889e-05, |
| "loss": 6.4831, |
| "mean_token_accuracy": 0.8755135674029588, |
| "num_tokens": 37057425.0, |
| "step": 4480 |
| }, |
| { |
| "entropy": 0.4117017044685781, |
| "epoch": 1.796, |
| "grad_norm": 51.5, |
| "learning_rate": 1.2246666666666667e-05, |
| "loss": 6.6424, |
| "mean_token_accuracy": 0.8731210798025131, |
| "num_tokens": 37141687.0, |
| "step": 4490 |
| }, |
| { |
| "entropy": 0.38369811829179523, |
| "epoch": 1.8, |
| "grad_norm": 36.75, |
| "learning_rate": 1.2224444444444445e-05, |
| "loss": 6.0253, |
| "mean_token_accuracy": 0.883763050287962, |
| "num_tokens": 37225440.0, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.8, |
| "eval_chemistry_entropy": 0.5401435644030571, |
| "eval_chemistry_loss": 0.6727893352508545, |
| "eval_chemistry_mean_token_accuracy": 0.8133891487121582, |
| "eval_chemistry_num_tokens": 37225440.0, |
| "eval_chemistry_runtime": 53.6064, |
| "eval_chemistry_samples_per_second": 9.327, |
| "eval_chemistry_steps_per_second": 9.327, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.8, |
| "eval_physics_entropy": 0.48808869475126265, |
| "eval_physics_loss": 0.5868460536003113, |
| "eval_physics_mean_token_accuracy": 0.8314950082302094, |
| "eval_physics_num_tokens": 37225440.0, |
| "eval_physics_runtime": 62.3476, |
| "eval_physics_samples_per_second": 8.02, |
| "eval_physics_steps_per_second": 8.02, |
| "step": 4500 |
| }, |
| { |
| "entropy": 0.3714961093850434, |
| "epoch": 1.804, |
| "grad_norm": 42.25, |
| "learning_rate": 1.2202222222222224e-05, |
| "loss": 6.1358, |
| "mean_token_accuracy": 0.8824129909276962, |
| "num_tokens": 37311306.0, |
| "step": 4510 |
| }, |
| { |
| "entropy": 0.4003173102624714, |
| "epoch": 1.808, |
| "grad_norm": 43.25, |
| "learning_rate": 1.218e-05, |
| "loss": 6.3433, |
| "mean_token_accuracy": 0.8767804615199566, |
| "num_tokens": 37395449.0, |
| "step": 4520 |
| }, |
| { |
| "entropy": 0.3983105253893882, |
| "epoch": 1.812, |
| "grad_norm": 49.0, |
| "learning_rate": 1.215777777777778e-05, |
| "loss": 6.332, |
| "mean_token_accuracy": 0.8774991031736136, |
| "num_tokens": 37478804.0, |
| "step": 4530 |
| }, |
| { |
| "entropy": 0.3816450200974941, |
| "epoch": 1.8159999999999998, |
| "grad_norm": 43.5, |
| "learning_rate": 1.2135555555555556e-05, |
| "loss": 6.243, |
| "mean_token_accuracy": 0.879349748045206, |
| "num_tokens": 37565463.0, |
| "step": 4540 |
| }, |
| { |
| "entropy": 0.41424746057018635, |
| "epoch": 1.8199999999999998, |
| "grad_norm": 44.0, |
| "learning_rate": 1.2113333333333335e-05, |
| "loss": 6.5729, |
| "mean_token_accuracy": 0.8759691219776868, |
| "num_tokens": 37647141.0, |
| "step": 4550 |
| }, |
| { |
| "entropy": 0.3897454238496721, |
| "epoch": 1.8239999999999998, |
| "grad_norm": 49.0, |
| "learning_rate": 1.209111111111111e-05, |
| "loss": 6.2392, |
| "mean_token_accuracy": 0.8819328770041466, |
| "num_tokens": 37729535.0, |
| "step": 4560 |
| }, |
| { |
| "entropy": 0.4377773189917207, |
| "epoch": 1.8279999999999998, |
| "grad_norm": 51.75, |
| "learning_rate": 1.206888888888889e-05, |
| "loss": 7.1286, |
| "mean_token_accuracy": 0.8668288454413414, |
| "num_tokens": 37807940.0, |
| "step": 4570 |
| }, |
| { |
| "entropy": 0.38501444049179556, |
| "epoch": 1.8319999999999999, |
| "grad_norm": 40.0, |
| "learning_rate": 1.204666666666667e-05, |
| "loss": 6.0622, |
| "mean_token_accuracy": 0.8835205603390932, |
| "num_tokens": 37888632.0, |
| "step": 4580 |
| }, |
| { |
| "entropy": 0.38747762781567874, |
| "epoch": 1.8359999999999999, |
| "grad_norm": 63.25, |
| "learning_rate": 1.2024444444444445e-05, |
| "loss": 6.4734, |
| "mean_token_accuracy": 0.8781172964721918, |
| "num_tokens": 37972144.0, |
| "step": 4590 |
| }, |
| { |
| "entropy": 0.3853580172173679, |
| "epoch": 1.8399999999999999, |
| "grad_norm": 39.0, |
| "learning_rate": 1.2002222222222225e-05, |
| "loss": 6.0641, |
| "mean_token_accuracy": 0.8832456823438406, |
| "num_tokens": 38057839.0, |
| "step": 4600 |
| }, |
| { |
| "epoch": 1.8399999999999999, |
| "eval_chemistry_entropy": 0.5565233428180217, |
| "eval_chemistry_loss": 0.6685209274291992, |
| "eval_chemistry_mean_token_accuracy": 0.8136617729663849, |
| "eval_chemistry_num_tokens": 38057839.0, |
| "eval_chemistry_runtime": 53.8992, |
| "eval_chemistry_samples_per_second": 9.277, |
| "eval_chemistry_steps_per_second": 9.277, |
| "step": 4600 |
| }, |
| { |
| "epoch": 1.8399999999999999, |
| "eval_physics_entropy": 0.5040034144669772, |
| "eval_physics_loss": 0.5828114151954651, |
| "eval_physics_mean_token_accuracy": 0.8316534082889557, |
| "eval_physics_num_tokens": 38057839.0, |
| "eval_physics_runtime": 62.7885, |
| "eval_physics_samples_per_second": 7.963, |
| "eval_physics_steps_per_second": 7.963, |
| "step": 4600 |
| }, |
| { |
| "entropy": 0.40128663945943116, |
| "epoch": 1.8439999999999999, |
| "grad_norm": 44.0, |
| "learning_rate": 1.198e-05, |
| "loss": 6.4715, |
| "mean_token_accuracy": 0.8770762640982867, |
| "num_tokens": 38141516.0, |
| "step": 4610 |
| }, |
| { |
| "entropy": 0.39252530760131776, |
| "epoch": 1.8479999999999999, |
| "grad_norm": 38.75, |
| "learning_rate": 1.195777777777778e-05, |
| "loss": 6.2283, |
| "mean_token_accuracy": 0.8780303739011288, |
| "num_tokens": 38228321.0, |
| "step": 4620 |
| }, |
| { |
| "entropy": 0.39332945430651306, |
| "epoch": 1.8519999999999999, |
| "grad_norm": 42.5, |
| "learning_rate": 1.1935555555555556e-05, |
| "loss": 6.3253, |
| "mean_token_accuracy": 0.8788463421165943, |
| "num_tokens": 38314672.0, |
| "step": 4630 |
| }, |
| { |
| "entropy": 0.37782758264802396, |
| "epoch": 1.8559999999999999, |
| "grad_norm": 48.5, |
| "learning_rate": 1.1913333333333335e-05, |
| "loss": 6.0889, |
| "mean_token_accuracy": 0.8834712006151676, |
| "num_tokens": 38398033.0, |
| "step": 4640 |
| }, |
| { |
| "entropy": 0.3893645564094186, |
| "epoch": 1.8599999999999999, |
| "grad_norm": 53.25, |
| "learning_rate": 1.1891111111111111e-05, |
| "loss": 6.2706, |
| "mean_token_accuracy": 0.8788041561841965, |
| "num_tokens": 38481584.0, |
| "step": 4650 |
| }, |
| { |
| "entropy": 0.4083589227870107, |
| "epoch": 1.8639999999999999, |
| "grad_norm": 43.25, |
| "learning_rate": 1.186888888888889e-05, |
| "loss": 6.5162, |
| "mean_token_accuracy": 0.8751051504164934, |
| "num_tokens": 38568933.0, |
| "step": 4660 |
| }, |
| { |
| "entropy": 0.38208632012829186, |
| "epoch": 1.8679999999999999, |
| "grad_norm": 42.5, |
| "learning_rate": 1.1846666666666668e-05, |
| "loss": 6.0292, |
| "mean_token_accuracy": 0.8837982200086116, |
| "num_tokens": 38646842.0, |
| "step": 4670 |
| }, |
| { |
| "entropy": 0.37446660036221147, |
| "epoch": 1.8719999999999999, |
| "grad_norm": 42.75, |
| "learning_rate": 1.1824444444444445e-05, |
| "loss": 6.0901, |
| "mean_token_accuracy": 0.8815959721803666, |
| "num_tokens": 38729203.0, |
| "step": 4680 |
| }, |
| { |
| "entropy": 0.39576807664707303, |
| "epoch": 1.876, |
| "grad_norm": 45.75, |
| "learning_rate": 1.1802222222222223e-05, |
| "loss": 6.2985, |
| "mean_token_accuracy": 0.8780396945774556, |
| "num_tokens": 38811533.0, |
| "step": 4690 |
| }, |
| { |
| "entropy": 0.3904746563639492, |
| "epoch": 1.88, |
| "grad_norm": 51.75, |
| "learning_rate": 1.178e-05, |
| "loss": 6.3537, |
| "mean_token_accuracy": 0.8788532923907042, |
| "num_tokens": 38895784.0, |
| "step": 4700 |
| }, |
| { |
| "epoch": 1.88, |
| "eval_chemistry_entropy": 0.549619193226099, |
| "eval_chemistry_loss": 0.6710554361343384, |
| "eval_chemistry_mean_token_accuracy": 0.8132365696430206, |
| "eval_chemistry_num_tokens": 38895784.0, |
| "eval_chemistry_runtime": 53.5414, |
| "eval_chemistry_samples_per_second": 9.339, |
| "eval_chemistry_steps_per_second": 9.339, |
| "step": 4700 |
| }, |
| { |
| "epoch": 1.88, |
| "eval_physics_entropy": 0.49999719807505605, |
| "eval_physics_loss": 0.583443820476532, |
| "eval_physics_mean_token_accuracy": 0.8320970281362533, |
| "eval_physics_num_tokens": 38895784.0, |
| "eval_physics_runtime": 62.3798, |
| "eval_physics_samples_per_second": 8.015, |
| "eval_physics_steps_per_second": 8.015, |
| "step": 4700 |
| }, |
| { |
| "entropy": 0.40091329999268055, |
| "epoch": 1.884, |
| "grad_norm": 41.75, |
| "learning_rate": 1.1757777777777778e-05, |
| "loss": 6.461, |
| "mean_token_accuracy": 0.8758362587541342, |
| "num_tokens": 38980934.0, |
| "step": 4710 |
| }, |
| { |
| "entropy": 0.3958409369457513, |
| "epoch": 1.888, |
| "grad_norm": 48.75, |
| "learning_rate": 1.1735555555555556e-05, |
| "loss": 6.3845, |
| "mean_token_accuracy": 0.8778816595673561, |
| "num_tokens": 39058791.0, |
| "step": 4720 |
| }, |
| { |
| "entropy": 0.4157537971623242, |
| "epoch": 1.892, |
| "grad_norm": 52.0, |
| "learning_rate": 1.1713333333333334e-05, |
| "loss": 6.7041, |
| "mean_token_accuracy": 0.8732577003538609, |
| "num_tokens": 39142381.0, |
| "step": 4730 |
| }, |
| { |
| "entropy": 0.3967838443815708, |
| "epoch": 1.896, |
| "grad_norm": 44.0, |
| "learning_rate": 1.1691111111111113e-05, |
| "loss": 6.4117, |
| "mean_token_accuracy": 0.8777343105524779, |
| "num_tokens": 39224201.0, |
| "step": 4740 |
| }, |
| { |
| "entropy": 0.4056083607487381, |
| "epoch": 1.9, |
| "grad_norm": 47.0, |
| "learning_rate": 1.1668888888888889e-05, |
| "loss": 6.5486, |
| "mean_token_accuracy": 0.874582264199853, |
| "num_tokens": 39305803.0, |
| "step": 4750 |
| }, |
| { |
| "entropy": 0.4043416635133326, |
| "epoch": 1.904, |
| "grad_norm": 55.25, |
| "learning_rate": 1.1646666666666668e-05, |
| "loss": 6.6009, |
| "mean_token_accuracy": 0.8759451858699322, |
| "num_tokens": 39386170.0, |
| "step": 4760 |
| }, |
| { |
| "entropy": 0.443442501546815, |
| "epoch": 1.908, |
| "grad_norm": 44.0, |
| "learning_rate": 1.1624444444444446e-05, |
| "loss": 7.0102, |
| "mean_token_accuracy": 0.8690990075469017, |
| "num_tokens": 39462457.0, |
| "step": 4770 |
| }, |
| { |
| "entropy": 0.4046101786196232, |
| "epoch": 1.912, |
| "grad_norm": 38.0, |
| "learning_rate": 1.1602222222222223e-05, |
| "loss": 6.5874, |
| "mean_token_accuracy": 0.8764791205525398, |
| "num_tokens": 39545061.0, |
| "step": 4780 |
| }, |
| { |
| "entropy": 0.39519280968233944, |
| "epoch": 1.916, |
| "grad_norm": 43.25, |
| "learning_rate": 1.1580000000000001e-05, |
| "loss": 6.3615, |
| "mean_token_accuracy": 0.8806503396481276, |
| "num_tokens": 39625674.0, |
| "step": 4790 |
| }, |
| { |
| "entropy": 0.37955069476738573, |
| "epoch": 1.92, |
| "grad_norm": 44.75, |
| "learning_rate": 1.1557777777777779e-05, |
| "loss": 5.9753, |
| "mean_token_accuracy": 0.8847485568374396, |
| "num_tokens": 39710381.0, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_chemistry_entropy": 0.5332140245437622, |
| "eval_chemistry_loss": 0.672716498374939, |
| "eval_chemistry_mean_token_accuracy": 0.814129298210144, |
| "eval_chemistry_num_tokens": 39710381.0, |
| "eval_chemistry_runtime": 53.5948, |
| "eval_chemistry_samples_per_second": 9.329, |
| "eval_chemistry_steps_per_second": 9.329, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_physics_entropy": 0.4877495141774416, |
| "eval_physics_loss": 0.5833487510681152, |
| "eval_physics_mean_token_accuracy": 0.8329446904063225, |
| "eval_physics_num_tokens": 39710381.0, |
| "eval_physics_runtime": 62.3184, |
| "eval_physics_samples_per_second": 8.023, |
| "eval_physics_steps_per_second": 8.023, |
| "step": 4800 |
| }, |
| { |
| "entropy": 0.4095441807992756, |
| "epoch": 1.924, |
| "grad_norm": 47.25, |
| "learning_rate": 1.1535555555555556e-05, |
| "loss": 6.7103, |
| "mean_token_accuracy": 0.8711355209350586, |
| "num_tokens": 39795382.0, |
| "step": 4810 |
| }, |
| { |
| "entropy": 0.4090301369316876, |
| "epoch": 1.928, |
| "grad_norm": 42.0, |
| "learning_rate": 1.1513333333333334e-05, |
| "loss": 6.4862, |
| "mean_token_accuracy": 0.8757699660956859, |
| "num_tokens": 39878408.0, |
| "step": 4820 |
| }, |
| { |
| "entropy": 0.40265353601425885, |
| "epoch": 1.932, |
| "grad_norm": 39.5, |
| "learning_rate": 1.1491111111111113e-05, |
| "loss": 6.5649, |
| "mean_token_accuracy": 0.8752508915960788, |
| "num_tokens": 39962873.0, |
| "step": 4830 |
| }, |
| { |
| "entropy": 0.3662755880970508, |
| "epoch": 1.936, |
| "grad_norm": 43.25, |
| "learning_rate": 1.1468888888888889e-05, |
| "loss": 5.8123, |
| "mean_token_accuracy": 0.8867810111492872, |
| "num_tokens": 40043354.0, |
| "step": 4840 |
| }, |
| { |
| "entropy": 0.38979168897494676, |
| "epoch": 1.94, |
| "grad_norm": 44.75, |
| "learning_rate": 1.1446666666666668e-05, |
| "loss": 6.3222, |
| "mean_token_accuracy": 0.8783317163586617, |
| "num_tokens": 40124736.0, |
| "step": 4850 |
| }, |
| { |
| "entropy": 0.37943958956748247, |
| "epoch": 1.944, |
| "grad_norm": 39.25, |
| "learning_rate": 1.1424444444444444e-05, |
| "loss": 5.9994, |
| "mean_token_accuracy": 0.8860078375786543, |
| "num_tokens": 40206607.0, |
| "step": 4860 |
| }, |
| { |
| "entropy": 0.3684364980086684, |
| "epoch": 1.948, |
| "grad_norm": 41.0, |
| "learning_rate": 1.1402222222222224e-05, |
| "loss": 5.9377, |
| "mean_token_accuracy": 0.8854397624731064, |
| "num_tokens": 40294013.0, |
| "step": 4870 |
| }, |
| { |
| "entropy": 0.38094157055020333, |
| "epoch": 1.952, |
| "grad_norm": 45.0, |
| "learning_rate": 1.138e-05, |
| "loss": 6.0475, |
| "mean_token_accuracy": 0.8843934826552868, |
| "num_tokens": 40375790.0, |
| "step": 4880 |
| }, |
| { |
| "entropy": 0.3802569825667888, |
| "epoch": 1.956, |
| "grad_norm": 50.25, |
| "learning_rate": 1.1357777777777779e-05, |
| "loss": 6.1904, |
| "mean_token_accuracy": 0.8817527800798416, |
| "num_tokens": 40455418.0, |
| "step": 4890 |
| }, |
| { |
| "entropy": 0.3788024752866477, |
| "epoch": 1.96, |
| "grad_norm": 59.25, |
| "learning_rate": 1.1335555555555558e-05, |
| "loss": 5.9998, |
| "mean_token_accuracy": 0.883975101262331, |
| "num_tokens": 40539856.0, |
| "step": 4900 |
| }, |
| { |
| "epoch": 1.96, |
| "eval_chemistry_entropy": 0.5327692772746087, |
| "eval_chemistry_loss": 0.6734102964401245, |
| "eval_chemistry_mean_token_accuracy": 0.8138529658317566, |
| "eval_chemistry_num_tokens": 40539856.0, |
| "eval_chemistry_runtime": 53.5819, |
| "eval_chemistry_samples_per_second": 9.332, |
| "eval_chemistry_steps_per_second": 9.332, |
| "step": 4900 |
| }, |
| { |
| "epoch": 1.96, |
| "eval_physics_entropy": 0.4875757833570242, |
| "eval_physics_loss": 0.5831025242805481, |
| "eval_physics_mean_token_accuracy": 0.8328130157589912, |
| "eval_physics_num_tokens": 40539856.0, |
| "eval_physics_runtime": 62.266, |
| "eval_physics_samples_per_second": 8.03, |
| "eval_physics_steps_per_second": 8.03, |
| "step": 4900 |
| }, |
| { |
| "entropy": 0.41536389514803884, |
| "epoch": 1.964, |
| "grad_norm": 62.5, |
| "learning_rate": 1.1313333333333334e-05, |
| "loss": 6.9138, |
| "mean_token_accuracy": 0.8712738990783692, |
| "num_tokens": 40621709.0, |
| "step": 4910 |
| }, |
| { |
| "entropy": 0.3926308457739651, |
| "epoch": 1.968, |
| "grad_norm": 48.75, |
| "learning_rate": 1.1291111111111113e-05, |
| "loss": 6.1219, |
| "mean_token_accuracy": 0.8826039176434278, |
| "num_tokens": 40705451.0, |
| "step": 4920 |
| }, |
| { |
| "entropy": 0.37549833627417684, |
| "epoch": 1.972, |
| "grad_norm": 44.25, |
| "learning_rate": 1.126888888888889e-05, |
| "loss": 6.1036, |
| "mean_token_accuracy": 0.8824028592556715, |
| "num_tokens": 40785961.0, |
| "step": 4930 |
| }, |
| { |
| "entropy": 0.3708323477767408, |
| "epoch": 1.976, |
| "grad_norm": 43.5, |
| "learning_rate": 1.1246666666666669e-05, |
| "loss": 5.9873, |
| "mean_token_accuracy": 0.884157856926322, |
| "num_tokens": 40873446.0, |
| "step": 4940 |
| }, |
| { |
| "entropy": 0.3954867236316204, |
| "epoch": 1.98, |
| "grad_norm": 37.25, |
| "learning_rate": 1.1224444444444444e-05, |
| "loss": 6.322, |
| "mean_token_accuracy": 0.8779752962291241, |
| "num_tokens": 40956433.0, |
| "step": 4950 |
| }, |
| { |
| "entropy": 0.3989587856456637, |
| "epoch": 1.984, |
| "grad_norm": 52.75, |
| "learning_rate": 1.1202222222222224e-05, |
| "loss": 6.5748, |
| "mean_token_accuracy": 0.8759325701743365, |
| "num_tokens": 41040313.0, |
| "step": 4960 |
| }, |
| { |
| "entropy": 0.4050182838924229, |
| "epoch": 1.988, |
| "grad_norm": 59.0, |
| "learning_rate": 1.1180000000000001e-05, |
| "loss": 6.448, |
| "mean_token_accuracy": 0.8787617024034262, |
| "num_tokens": 41124137.0, |
| "step": 4970 |
| }, |
| { |
| "entropy": 0.39617609707638624, |
| "epoch": 1.992, |
| "grad_norm": 44.0, |
| "learning_rate": 1.1157777777777779e-05, |
| "loss": 6.4284, |
| "mean_token_accuracy": 0.8796563293784857, |
| "num_tokens": 41205940.0, |
| "step": 4980 |
| }, |
| { |
| "entropy": 0.3897817573044449, |
| "epoch": 1.996, |
| "grad_norm": 45.75, |
| "learning_rate": 1.1135555555555557e-05, |
| "loss": 6.2676, |
| "mean_token_accuracy": 0.8792812936007977, |
| "num_tokens": 41292121.0, |
| "step": 4990 |
| }, |
| { |
| "entropy": 0.39420619974844157, |
| "epoch": 2.0, |
| "grad_norm": 50.0, |
| "learning_rate": 1.1113333333333334e-05, |
| "loss": 6.1989, |
| "mean_token_accuracy": 0.8807359039783478, |
| "num_tokens": 41373608.0, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_chemistry_entropy": 0.5424425678253174, |
| "eval_chemistry_loss": 0.668811023235321, |
| "eval_chemistry_mean_token_accuracy": 0.8141675420999527, |
| "eval_chemistry_num_tokens": 41373608.0, |
| "eval_chemistry_runtime": 53.429, |
| "eval_chemistry_samples_per_second": 9.358, |
| "eval_chemistry_steps_per_second": 9.358, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_physics_entropy": 0.49732374693453313, |
| "eval_physics_loss": 0.5799261331558228, |
| "eval_physics_mean_token_accuracy": 0.833329997241497, |
| "eval_physics_num_tokens": 41373608.0, |
| "eval_physics_runtime": 62.3748, |
| "eval_physics_samples_per_second": 8.016, |
| "eval_physics_steps_per_second": 8.016, |
| "step": 5000 |
| }, |
| { |
| "entropy": 0.23874019854702055, |
| "epoch": 2.004, |
| "grad_norm": 58.75, |
| "learning_rate": 1.1091111111111112e-05, |
| "loss": 3.3263, |
| "mean_token_accuracy": 0.9352266754955053, |
| "num_tokens": 41457392.0, |
| "step": 5010 |
| }, |
| { |
| "entropy": 0.17612766423262655, |
| "epoch": 2.008, |
| "grad_norm": 56.5, |
| "learning_rate": 1.106888888888889e-05, |
| "loss": 3.134, |
| "mean_token_accuracy": 0.9380614425987005, |
| "num_tokens": 41541054.0, |
| "step": 5020 |
| }, |
| { |
| "entropy": 0.2073903985787183, |
| "epoch": 2.012, |
| "grad_norm": 47.5, |
| "learning_rate": 1.1046666666666667e-05, |
| "loss": 3.0936, |
| "mean_token_accuracy": 0.9398012980818748, |
| "num_tokens": 41621648.0, |
| "step": 5030 |
| }, |
| { |
| "entropy": 0.19466686681844295, |
| "epoch": 2.016, |
| "grad_norm": 43.75, |
| "learning_rate": 1.1024444444444445e-05, |
| "loss": 3.1081, |
| "mean_token_accuracy": 0.9395533055067062, |
| "num_tokens": 41708226.0, |
| "step": 5040 |
| }, |
| { |
| "entropy": 0.19641057420521973, |
| "epoch": 2.02, |
| "grad_norm": 55.0, |
| "learning_rate": 1.1002222222222222e-05, |
| "loss": 3.1071, |
| "mean_token_accuracy": 0.9384653646498918, |
| "num_tokens": 41789805.0, |
| "step": 5050 |
| }, |
| { |
| "entropy": 0.1920419150032103, |
| "epoch": 2.024, |
| "grad_norm": 46.5, |
| "learning_rate": 1.0980000000000002e-05, |
| "loss": 3.0469, |
| "mean_token_accuracy": 0.9404902808368206, |
| "num_tokens": 41874459.0, |
| "step": 5060 |
| }, |
| { |
| "entropy": 0.20032177697867154, |
| "epoch": 2.028, |
| "grad_norm": 41.75, |
| "learning_rate": 1.0957777777777778e-05, |
| "loss": 3.2179, |
| "mean_token_accuracy": 0.9377676222473383, |
| "num_tokens": 41962010.0, |
| "step": 5070 |
| }, |
| { |
| "entropy": 0.20085438918322324, |
| "epoch": 2.032, |
| "grad_norm": 47.25, |
| "learning_rate": 1.0935555555555557e-05, |
| "loss": 3.1985, |
| "mean_token_accuracy": 0.9379490800201893, |
| "num_tokens": 42045433.0, |
| "step": 5080 |
| }, |
| { |
| "entropy": 0.19083389090374112, |
| "epoch": 2.036, |
| "grad_norm": 45.25, |
| "learning_rate": 1.0913333333333333e-05, |
| "loss": 3.0181, |
| "mean_token_accuracy": 0.9398705091327428, |
| "num_tokens": 42131377.0, |
| "step": 5090 |
| }, |
| { |
| "entropy": 0.19753868989646434, |
| "epoch": 2.04, |
| "grad_norm": 44.5, |
| "learning_rate": 1.0891111111111112e-05, |
| "loss": 3.0686, |
| "mean_token_accuracy": 0.9392331838607788, |
| "num_tokens": 42208657.0, |
| "step": 5100 |
| }, |
| { |
| "epoch": 2.04, |
| "eval_chemistry_entropy": 0.41862027600407603, |
| "eval_chemistry_loss": 0.7625600695610046, |
| "eval_chemistry_mean_token_accuracy": 0.809203598678112, |
| "eval_chemistry_num_tokens": 42208657.0, |
| "eval_chemistry_runtime": 54.1132, |
| "eval_chemistry_samples_per_second": 9.24, |
| "eval_chemistry_steps_per_second": 9.24, |
| "step": 5100 |
| }, |
| { |
| "epoch": 2.04, |
| "eval_physics_entropy": 0.3989468842595816, |
| "eval_physics_loss": 0.6450238227844238, |
| "eval_physics_mean_token_accuracy": 0.8284254409670829, |
| "eval_physics_num_tokens": 42208657.0, |
| "eval_physics_runtime": 62.6425, |
| "eval_physics_samples_per_second": 7.982, |
| "eval_physics_steps_per_second": 7.982, |
| "step": 5100 |
| }, |
| { |
| "entropy": 0.20550553721841425, |
| "epoch": 2.044, |
| "grad_norm": 43.5, |
| "learning_rate": 1.0868888888888888e-05, |
| "loss": 3.296, |
| "mean_token_accuracy": 0.9357010770589114, |
| "num_tokens": 42289517.0, |
| "step": 5110 |
| }, |
| { |
| "entropy": 0.19961890419945122, |
| "epoch": 2.048, |
| "grad_norm": 60.75, |
| "learning_rate": 1.0846666666666667e-05, |
| "loss": 3.1818, |
| "mean_token_accuracy": 0.9377218190580606, |
| "num_tokens": 42372694.0, |
| "step": 5120 |
| }, |
| { |
| "entropy": 0.20033283510711045, |
| "epoch": 2.052, |
| "grad_norm": 48.5, |
| "learning_rate": 1.0824444444444447e-05, |
| "loss": 3.1738, |
| "mean_token_accuracy": 0.9384920679032802, |
| "num_tokens": 42458003.0, |
| "step": 5130 |
| }, |
| { |
| "entropy": 0.1853128487477079, |
| "epoch": 2.056, |
| "grad_norm": 46.5, |
| "learning_rate": 1.0802222222222223e-05, |
| "loss": 3.0728, |
| "mean_token_accuracy": 0.9401571858674288, |
| "num_tokens": 42541126.0, |
| "step": 5140 |
| }, |
| { |
| "entropy": 0.20658304239623249, |
| "epoch": 2.06, |
| "grad_norm": 61.25, |
| "learning_rate": 1.0780000000000002e-05, |
| "loss": 3.2669, |
| "mean_token_accuracy": 0.9361684795469045, |
| "num_tokens": 42629304.0, |
| "step": 5150 |
| }, |
| { |
| "entropy": 0.20088807311840357, |
| "epoch": 2.064, |
| "grad_norm": 41.0, |
| "learning_rate": 1.0757777777777778e-05, |
| "loss": 3.1508, |
| "mean_token_accuracy": 0.938087810203433, |
| "num_tokens": 42710240.0, |
| "step": 5160 |
| }, |
| { |
| "entropy": 0.19043276484590024, |
| "epoch": 2.068, |
| "grad_norm": 46.75, |
| "learning_rate": 1.0735555555555557e-05, |
| "loss": 3.1074, |
| "mean_token_accuracy": 0.9401311114430427, |
| "num_tokens": 42792801.0, |
| "step": 5170 |
| }, |
| { |
| "entropy": 0.20087013996671885, |
| "epoch": 2.072, |
| "grad_norm": 48.25, |
| "learning_rate": 1.0713333333333333e-05, |
| "loss": 3.1866, |
| "mean_token_accuracy": 0.9368706427514553, |
| "num_tokens": 42874781.0, |
| "step": 5180 |
| }, |
| { |
| "entropy": 0.19184604636393487, |
| "epoch": 2.076, |
| "grad_norm": 50.0, |
| "learning_rate": 1.0691111111111112e-05, |
| "loss": 3.0469, |
| "mean_token_accuracy": 0.9403921004384757, |
| "num_tokens": 42957730.0, |
| "step": 5190 |
| }, |
| { |
| "entropy": 0.20260196740273387, |
| "epoch": 2.08, |
| "grad_norm": 47.25, |
| "learning_rate": 1.0668888888888892e-05, |
| "loss": 3.2253, |
| "mean_token_accuracy": 0.9380486860871315, |
| "num_tokens": 43037844.0, |
| "step": 5200 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_chemistry_entropy": 0.4037852519154549, |
| "eval_chemistry_loss": 0.7827287912368774, |
| "eval_chemistry_mean_token_accuracy": 0.8081873996853829, |
| "eval_chemistry_num_tokens": 43037844.0, |
| "eval_chemistry_runtime": 53.8385, |
| "eval_chemistry_samples_per_second": 9.287, |
| "eval_chemistry_steps_per_second": 9.287, |
| "step": 5200 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_physics_entropy": 0.3873061000108719, |
| "eval_physics_loss": 0.6558912396430969, |
| "eval_physics_mean_token_accuracy": 0.8283050252199173, |
| "eval_physics_num_tokens": 43037844.0, |
| "eval_physics_runtime": 62.4627, |
| "eval_physics_samples_per_second": 8.005, |
| "eval_physics_steps_per_second": 8.005, |
| "step": 5200 |
| }, |
| { |
| "entropy": 0.20824256259948015, |
| "epoch": 2.084, |
| "grad_norm": 48.0, |
| "learning_rate": 1.0646666666666668e-05, |
| "loss": 3.4052, |
| "mean_token_accuracy": 0.9333480909466744, |
| "num_tokens": 43123325.0, |
| "step": 5210 |
| }, |
| { |
| "entropy": 0.19789786953479052, |
| "epoch": 2.088, |
| "grad_norm": 56.75, |
| "learning_rate": 1.0624444444444447e-05, |
| "loss": 3.0033, |
| "mean_token_accuracy": 0.9417567845433951, |
| "num_tokens": 43202298.0, |
| "step": 5220 |
| }, |
| { |
| "entropy": 0.20151855589356274, |
| "epoch": 2.092, |
| "grad_norm": 48.75, |
| "learning_rate": 1.0602222222222223e-05, |
| "loss": 3.2207, |
| "mean_token_accuracy": 0.938299423828721, |
| "num_tokens": 43285598.0, |
| "step": 5230 |
| }, |
| { |
| "entropy": 0.1916871007764712, |
| "epoch": 2.096, |
| "grad_norm": 46.0, |
| "learning_rate": 1.0580000000000002e-05, |
| "loss": 3.0968, |
| "mean_token_accuracy": 0.9383008874952793, |
| "num_tokens": 43368675.0, |
| "step": 5240 |
| }, |
| { |
| "entropy": 0.18731462587602438, |
| "epoch": 2.1, |
| "grad_norm": 53.5, |
| "learning_rate": 1.0557777777777778e-05, |
| "loss": 2.9798, |
| "mean_token_accuracy": 0.9430658213794232, |
| "num_tokens": 43449954.0, |
| "step": 5250 |
| }, |
| { |
| "entropy": 0.18388683935627342, |
| "epoch": 2.104, |
| "grad_norm": 54.25, |
| "learning_rate": 1.0535555555555557e-05, |
| "loss": 2.9247, |
| "mean_token_accuracy": 0.942484200373292, |
| "num_tokens": 43528580.0, |
| "step": 5260 |
| }, |
| { |
| "entropy": 0.1879286190494895, |
| "epoch": 2.108, |
| "grad_norm": 43.5, |
| "learning_rate": 1.0513333333333333e-05, |
| "loss": 3.0419, |
| "mean_token_accuracy": 0.9407990373671055, |
| "num_tokens": 43612977.0, |
| "step": 5270 |
| }, |
| { |
| "entropy": 0.19514538389630615, |
| "epoch": 2.112, |
| "grad_norm": 44.5, |
| "learning_rate": 1.0491111111111112e-05, |
| "loss": 3.1495, |
| "mean_token_accuracy": 0.9373606648296118, |
| "num_tokens": 43699544.0, |
| "step": 5280 |
| }, |
| { |
| "entropy": 0.19012615643441677, |
| "epoch": 2.116, |
| "grad_norm": 55.0, |
| "learning_rate": 1.046888888888889e-05, |
| "loss": 2.9851, |
| "mean_token_accuracy": 0.9408463139086962, |
| "num_tokens": 43776161.0, |
| "step": 5290 |
| }, |
| { |
| "entropy": 0.20069221341982485, |
| "epoch": 2.12, |
| "grad_norm": 47.25, |
| "learning_rate": 1.0446666666666668e-05, |
| "loss": 3.1781, |
| "mean_token_accuracy": 0.9359448026865721, |
| "num_tokens": 43858502.0, |
| "step": 5300 |
| }, |
| { |
| "epoch": 2.12, |
| "eval_chemistry_entropy": 0.40047966596484186, |
| "eval_chemistry_loss": 0.7848058938980103, |
| "eval_chemistry_mean_token_accuracy": 0.8079274354577064, |
| "eval_chemistry_num_tokens": 43858502.0, |
| "eval_chemistry_runtime": 53.5898, |
| "eval_chemistry_samples_per_second": 9.33, |
| "eval_chemistry_steps_per_second": 9.33, |
| "step": 5300 |
| }, |
| { |
| "epoch": 2.12, |
| "eval_physics_entropy": 0.38767903473973275, |
| "eval_physics_loss": 0.6546861529350281, |
| "eval_physics_mean_token_accuracy": 0.8277567273378372, |
| "eval_physics_num_tokens": 43858502.0, |
| "eval_physics_runtime": 62.343, |
| "eval_physics_samples_per_second": 8.02, |
| "eval_physics_steps_per_second": 8.02, |
| "step": 5300 |
| }, |
| { |
| "entropy": 0.20158565249294041, |
| "epoch": 2.124, |
| "grad_norm": 50.75, |
| "learning_rate": 1.0424444444444445e-05, |
| "loss": 3.1985, |
| "mean_token_accuracy": 0.9388665832579136, |
| "num_tokens": 43935182.0, |
| "step": 5310 |
| }, |
| { |
| "entropy": 0.1834682718385011, |
| "epoch": 2.128, |
| "grad_norm": 50.75, |
| "learning_rate": 1.0402222222222223e-05, |
| "loss": 2.9141, |
| "mean_token_accuracy": 0.9433030698448419, |
| "num_tokens": 44012632.0, |
| "step": 5320 |
| }, |
| { |
| "entropy": 0.20906293289735914, |
| "epoch": 2.132, |
| "grad_norm": 52.0, |
| "learning_rate": 1.038e-05, |
| "loss": 3.3272, |
| "mean_token_accuracy": 0.935481233894825, |
| "num_tokens": 44096016.0, |
| "step": 5330 |
| }, |
| { |
| "entropy": 0.18296956168487669, |
| "epoch": 2.136, |
| "grad_norm": 48.0, |
| "learning_rate": 1.0357777777777778e-05, |
| "loss": 2.9511, |
| "mean_token_accuracy": 0.9421849232167006, |
| "num_tokens": 44179301.0, |
| "step": 5340 |
| }, |
| { |
| "entropy": 0.208326399885118, |
| "epoch": 2.14, |
| "grad_norm": 63.0, |
| "learning_rate": 1.0335555555555556e-05, |
| "loss": 3.3295, |
| "mean_token_accuracy": 0.9351174153387547, |
| "num_tokens": 44264155.0, |
| "step": 5350 |
| }, |
| { |
| "entropy": 0.19738043893594295, |
| "epoch": 2.144, |
| "grad_norm": 41.25, |
| "learning_rate": 1.0313333333333335e-05, |
| "loss": 3.2062, |
| "mean_token_accuracy": 0.9371892511844635, |
| "num_tokens": 44349732.0, |
| "step": 5360 |
| }, |
| { |
| "entropy": 0.20311750478576868, |
| "epoch": 2.148, |
| "grad_norm": 50.0, |
| "learning_rate": 1.0291111111111111e-05, |
| "loss": 3.2275, |
| "mean_token_accuracy": 0.9368093464523554, |
| "num_tokens": 44431991.0, |
| "step": 5370 |
| }, |
| { |
| "entropy": 0.20572135057300328, |
| "epoch": 2.152, |
| "grad_norm": 48.75, |
| "learning_rate": 1.026888888888889e-05, |
| "loss": 3.2749, |
| "mean_token_accuracy": 0.9358561307191848, |
| "num_tokens": 44514865.0, |
| "step": 5380 |
| }, |
| { |
| "entropy": 0.20425092987716198, |
| "epoch": 2.156, |
| "grad_norm": 46.0, |
| "learning_rate": 1.0246666666666666e-05, |
| "loss": 3.1763, |
| "mean_token_accuracy": 0.9385301012545824, |
| "num_tokens": 44596124.0, |
| "step": 5390 |
| }, |
| { |
| "entropy": 0.20146920066326857, |
| "epoch": 2.16, |
| "grad_norm": 46.0, |
| "learning_rate": 1.0224444444444446e-05, |
| "loss": 3.2178, |
| "mean_token_accuracy": 0.9376044973731041, |
| "num_tokens": 44680410.0, |
| "step": 5400 |
| }, |
| { |
| "epoch": 2.16, |
| "eval_chemistry_entropy": 0.3856977616250515, |
| "eval_chemistry_loss": 0.798565685749054, |
| "eval_chemistry_mean_token_accuracy": 0.8074681994318962, |
| "eval_chemistry_num_tokens": 44680410.0, |
| "eval_chemistry_runtime": 53.5194, |
| "eval_chemistry_samples_per_second": 9.342, |
| "eval_chemistry_steps_per_second": 9.342, |
| "step": 5400 |
| }, |
| { |
| "epoch": 2.16, |
| "eval_physics_entropy": 0.3756562244296074, |
| "eval_physics_loss": 0.6638210415840149, |
| "eval_physics_mean_token_accuracy": 0.827698894739151, |
| "eval_physics_num_tokens": 44680410.0, |
| "eval_physics_runtime": 62.2773, |
| "eval_physics_samples_per_second": 8.029, |
| "eval_physics_steps_per_second": 8.029, |
| "step": 5400 |
| }, |
| { |
| "entropy": 0.18812919512856752, |
| "epoch": 2.164, |
| "grad_norm": 54.75, |
| "learning_rate": 1.0202222222222221e-05, |
| "loss": 3.0064, |
| "mean_token_accuracy": 0.9413947004824876, |
| "num_tokens": 44762582.0, |
| "step": 5410 |
| }, |
| { |
| "entropy": 0.19338072049431504, |
| "epoch": 2.168, |
| "grad_norm": 50.25, |
| "learning_rate": 1.018e-05, |
| "loss": 3.0948, |
| "mean_token_accuracy": 0.9408847827464342, |
| "num_tokens": 44846515.0, |
| "step": 5420 |
| }, |
| { |
| "entropy": 0.21481295677367598, |
| "epoch": 2.172, |
| "grad_norm": 58.5, |
| "learning_rate": 1.0157777777777777e-05, |
| "loss": 3.4678, |
| "mean_token_accuracy": 0.9332882829010487, |
| "num_tokens": 44932293.0, |
| "step": 5430 |
| }, |
| { |
| "entropy": 0.19565081875771284, |
| "epoch": 2.176, |
| "grad_norm": 44.25, |
| "learning_rate": 1.0135555555555556e-05, |
| "loss": 3.1546, |
| "mean_token_accuracy": 0.9388003278523683, |
| "num_tokens": 45017922.0, |
| "step": 5440 |
| }, |
| { |
| "entropy": 0.1895020380616188, |
| "epoch": 2.18, |
| "grad_norm": 48.5, |
| "learning_rate": 1.0113333333333335e-05, |
| "loss": 2.9332, |
| "mean_token_accuracy": 0.9421345889568329, |
| "num_tokens": 45099844.0, |
| "step": 5450 |
| }, |
| { |
| "entropy": 0.18103633744176478, |
| "epoch": 2.184, |
| "grad_norm": 50.0, |
| "learning_rate": 1.0091111111111111e-05, |
| "loss": 2.8778, |
| "mean_token_accuracy": 0.9432444013655186, |
| "num_tokens": 45181823.0, |
| "step": 5460 |
| }, |
| { |
| "entropy": 0.19471350284293293, |
| "epoch": 2.188, |
| "grad_norm": 51.5, |
| "learning_rate": 1.006888888888889e-05, |
| "loss": 3.1432, |
| "mean_token_accuracy": 0.9383002948015928, |
| "num_tokens": 45263197.0, |
| "step": 5470 |
| }, |
| { |
| "entropy": 0.20217982549220323, |
| "epoch": 2.192, |
| "grad_norm": 45.0, |
| "learning_rate": 1.0046666666666666e-05, |
| "loss": 3.2241, |
| "mean_token_accuracy": 0.9373363882303238, |
| "num_tokens": 45348179.0, |
| "step": 5480 |
| }, |
| { |
| "entropy": 0.19005100564099847, |
| "epoch": 2.196, |
| "grad_norm": 42.25, |
| "learning_rate": 1.0024444444444446e-05, |
| "loss": 2.9879, |
| "mean_token_accuracy": 0.9420632436871529, |
| "num_tokens": 45432770.0, |
| "step": 5490 |
| }, |
| { |
| "entropy": 0.18858733554370702, |
| "epoch": 2.2, |
| "grad_norm": 46.25, |
| "learning_rate": 1.0002222222222222e-05, |
| "loss": 3.0609, |
| "mean_token_accuracy": 0.93999606333673, |
| "num_tokens": 45514208.0, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.2, |
| "eval_chemistry_entropy": 0.39155059492588046, |
| "eval_chemistry_loss": 0.7910591959953308, |
| "eval_chemistry_mean_token_accuracy": 0.8080245018601417, |
| "eval_chemistry_num_tokens": 45514208.0, |
| "eval_chemistry_runtime": 53.4757, |
| "eval_chemistry_samples_per_second": 9.35, |
| "eval_chemistry_steps_per_second": 9.35, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.2, |
| "eval_physics_entropy": 0.3800457211136818, |
| "eval_physics_loss": 0.6611268520355225, |
| "eval_physics_mean_token_accuracy": 0.8281381183862686, |
| "eval_physics_num_tokens": 45514208.0, |
| "eval_physics_runtime": 62.3015, |
| "eval_physics_samples_per_second": 8.025, |
| "eval_physics_steps_per_second": 8.025, |
| "step": 5500 |
| }, |
| { |
| "entropy": 0.18614862819667904, |
| "epoch": 2.204, |
| "grad_norm": 44.0, |
| "learning_rate": 9.980000000000001e-06, |
| "loss": 2.9873, |
| "mean_token_accuracy": 0.942183205112815, |
| "num_tokens": 45596551.0, |
| "step": 5510 |
| }, |
| { |
| "entropy": 0.19601450096815826, |
| "epoch": 2.208, |
| "grad_norm": 53.0, |
| "learning_rate": 9.957777777777779e-06, |
| "loss": 3.1129, |
| "mean_token_accuracy": 0.9396491654217243, |
| "num_tokens": 45678397.0, |
| "step": 5520 |
| }, |
| { |
| "entropy": 0.19701245347969235, |
| "epoch": 2.212, |
| "grad_norm": 57.0, |
| "learning_rate": 9.935555555555556e-06, |
| "loss": 3.1407, |
| "mean_token_accuracy": 0.9378465551882982, |
| "num_tokens": 45762516.0, |
| "step": 5530 |
| }, |
| { |
| "entropy": 0.1893465863307938, |
| "epoch": 2.216, |
| "grad_norm": 53.5, |
| "learning_rate": 9.913333333333334e-06, |
| "loss": 3.0102, |
| "mean_token_accuracy": 0.9404071982949972, |
| "num_tokens": 45844632.0, |
| "step": 5540 |
| }, |
| { |
| "entropy": 0.19602622296661137, |
| "epoch": 2.22, |
| "grad_norm": 43.75, |
| "learning_rate": 9.891111111111113e-06, |
| "loss": 3.1011, |
| "mean_token_accuracy": 0.9404466662555933, |
| "num_tokens": 45925356.0, |
| "step": 5550 |
| }, |
| { |
| "entropy": 0.2090798495337367, |
| "epoch": 2.224, |
| "grad_norm": 52.25, |
| "learning_rate": 9.86888888888889e-06, |
| "loss": 3.3086, |
| "mean_token_accuracy": 0.9340983040630817, |
| "num_tokens": 46010052.0, |
| "step": 5560 |
| }, |
| { |
| "entropy": 0.19277014466933906, |
| "epoch": 2.228, |
| "grad_norm": 48.0, |
| "learning_rate": 9.846666666666668e-06, |
| "loss": 3.0988, |
| "mean_token_accuracy": 0.9395745355635882, |
| "num_tokens": 46096605.0, |
| "step": 5570 |
| }, |
| { |
| "entropy": 0.20378333488479256, |
| "epoch": 2.232, |
| "grad_norm": 54.25, |
| "learning_rate": 9.824444444444446e-06, |
| "loss": 3.2394, |
| "mean_token_accuracy": 0.9365138337016106, |
| "num_tokens": 46176730.0, |
| "step": 5580 |
| }, |
| { |
| "entropy": 0.20600440469570458, |
| "epoch": 2.2359999999999998, |
| "grad_norm": 42.5, |
| "learning_rate": 9.802222222222224e-06, |
| "loss": 3.2901, |
| "mean_token_accuracy": 0.9340278003364801, |
| "num_tokens": 46262197.0, |
| "step": 5590 |
| }, |
| { |
| "entropy": 0.20139261563308536, |
| "epoch": 2.24, |
| "grad_norm": 42.5, |
| "learning_rate": 9.780000000000001e-06, |
| "loss": 3.1502, |
| "mean_token_accuracy": 0.9389533422887325, |
| "num_tokens": 46347116.0, |
| "step": 5600 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_chemistry_entropy": 0.3909877706617117, |
| "eval_chemistry_loss": 0.7910385131835938, |
| "eval_chemistry_mean_token_accuracy": 0.8081122170090675, |
| "eval_chemistry_num_tokens": 46347116.0, |
| "eval_chemistry_runtime": 53.5591, |
| "eval_chemistry_samples_per_second": 9.335, |
| "eval_chemistry_steps_per_second": 9.335, |
| "step": 5600 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_physics_entropy": 0.3792251762896776, |
| "eval_physics_loss": 0.6604795455932617, |
| "eval_physics_mean_token_accuracy": 0.8283513634800911, |
| "eval_physics_num_tokens": 46347116.0, |
| "eval_physics_runtime": 62.3061, |
| "eval_physics_samples_per_second": 8.025, |
| "eval_physics_steps_per_second": 8.025, |
| "step": 5600 |
| }, |
| { |
| "entropy": 0.18947711491491645, |
| "epoch": 2.2439999999999998, |
| "grad_norm": 47.25, |
| "learning_rate": 9.757777777777779e-06, |
| "loss": 3.1396, |
| "mean_token_accuracy": 0.9386544648557902, |
| "num_tokens": 46429703.0, |
| "step": 5610 |
| }, |
| { |
| "entropy": 0.21070674285292626, |
| "epoch": 2.248, |
| "grad_norm": 61.25, |
| "learning_rate": 9.735555555555556e-06, |
| "loss": 3.3304, |
| "mean_token_accuracy": 0.935748977959156, |
| "num_tokens": 46513696.0, |
| "step": 5620 |
| }, |
| { |
| "entropy": 0.19108673203736543, |
| "epoch": 2.252, |
| "grad_norm": 54.25, |
| "learning_rate": 9.713333333333334e-06, |
| "loss": 3.0523, |
| "mean_token_accuracy": 0.9410431899130345, |
| "num_tokens": 46595828.0, |
| "step": 5630 |
| }, |
| { |
| "entropy": 0.192821927042678, |
| "epoch": 2.2560000000000002, |
| "grad_norm": 48.75, |
| "learning_rate": 9.691111111111112e-06, |
| "loss": 3.0979, |
| "mean_token_accuracy": 0.9399061404168606, |
| "num_tokens": 46673074.0, |
| "step": 5640 |
| }, |
| { |
| "entropy": 0.18479047757573425, |
| "epoch": 2.26, |
| "grad_norm": 48.25, |
| "learning_rate": 9.66888888888889e-06, |
| "loss": 3.0073, |
| "mean_token_accuracy": 0.9392396967858077, |
| "num_tokens": 46755709.0, |
| "step": 5650 |
| }, |
| { |
| "entropy": 0.212563668936491, |
| "epoch": 2.2640000000000002, |
| "grad_norm": 57.75, |
| "learning_rate": 9.646666666666667e-06, |
| "loss": 3.2538, |
| "mean_token_accuracy": 0.9364705868065357, |
| "num_tokens": 46841474.0, |
| "step": 5660 |
| }, |
| { |
| "entropy": 0.19083552088122815, |
| "epoch": 2.268, |
| "grad_norm": 49.0, |
| "learning_rate": 9.624444444444445e-06, |
| "loss": 3.0806, |
| "mean_token_accuracy": 0.9388643242418766, |
| "num_tokens": 46927376.0, |
| "step": 5670 |
| }, |
| { |
| "entropy": 0.19668898060917855, |
| "epoch": 2.2720000000000002, |
| "grad_norm": 48.0, |
| "learning_rate": 9.602222222222222e-06, |
| "loss": 3.1726, |
| "mean_token_accuracy": 0.9378286074846983, |
| "num_tokens": 47009386.0, |
| "step": 5680 |
| }, |
| { |
| "entropy": 0.1988459188491106, |
| "epoch": 2.276, |
| "grad_norm": 56.75, |
| "learning_rate": 9.58e-06, |
| "loss": 3.1352, |
| "mean_token_accuracy": 0.9398025307804346, |
| "num_tokens": 47091981.0, |
| "step": 5690 |
| }, |
| { |
| "entropy": 0.1950016777962446, |
| "epoch": 2.2800000000000002, |
| "grad_norm": 55.25, |
| "learning_rate": 9.557777777777777e-06, |
| "loss": 3.1477, |
| "mean_token_accuracy": 0.9378086104989052, |
| "num_tokens": 47175754.0, |
| "step": 5700 |
| }, |
| { |
| "epoch": 2.2800000000000002, |
| "eval_chemistry_entropy": 0.3963790101259947, |
| "eval_chemistry_loss": 0.7890461683273315, |
| "eval_chemistry_mean_token_accuracy": 0.8081274604797364, |
| "eval_chemistry_num_tokens": 47175754.0, |
| "eval_chemistry_runtime": 53.5499, |
| "eval_chemistry_samples_per_second": 9.337, |
| "eval_chemistry_steps_per_second": 9.337, |
| "step": 5700 |
| }, |
| { |
| "epoch": 2.2800000000000002, |
| "eval_physics_entropy": 0.3893430581241846, |
| "eval_physics_loss": 0.6548593044281006, |
| "eval_physics_mean_token_accuracy": 0.8284097356200218, |
| "eval_physics_num_tokens": 47175754.0, |
| "eval_physics_runtime": 62.376, |
| "eval_physics_samples_per_second": 8.016, |
| "eval_physics_steps_per_second": 8.016, |
| "step": 5700 |
| }, |
| { |
| "entropy": 0.20085035017691552, |
| "epoch": 2.284, |
| "grad_norm": 52.75, |
| "learning_rate": 9.535555555555557e-06, |
| "loss": 3.2197, |
| "mean_token_accuracy": 0.9371700089424848, |
| "num_tokens": 47262872.0, |
| "step": 5710 |
| }, |
| { |
| "entropy": 0.20114704947918655, |
| "epoch": 2.288, |
| "grad_norm": 53.75, |
| "learning_rate": 9.513333333333334e-06, |
| "loss": 3.2122, |
| "mean_token_accuracy": 0.9378445014357567, |
| "num_tokens": 47344231.0, |
| "step": 5720 |
| }, |
| { |
| "entropy": 0.1871094464790076, |
| "epoch": 2.292, |
| "grad_norm": 55.0, |
| "learning_rate": 9.491111111111112e-06, |
| "loss": 2.9673, |
| "mean_token_accuracy": 0.9426150672137737, |
| "num_tokens": 47425711.0, |
| "step": 5730 |
| }, |
| { |
| "entropy": 0.197967362171039, |
| "epoch": 2.296, |
| "grad_norm": 45.5, |
| "learning_rate": 9.46888888888889e-06, |
| "loss": 3.1839, |
| "mean_token_accuracy": 0.9377172753214836, |
| "num_tokens": 47507052.0, |
| "step": 5740 |
| }, |
| { |
| "entropy": 0.19870077301748096, |
| "epoch": 2.3, |
| "grad_norm": 43.25, |
| "learning_rate": 9.446666666666667e-06, |
| "loss": 3.1619, |
| "mean_token_accuracy": 0.9375291150063276, |
| "num_tokens": 47584179.0, |
| "step": 5750 |
| }, |
| { |
| "entropy": 0.19026125948876144, |
| "epoch": 2.304, |
| "grad_norm": 52.5, |
| "learning_rate": 9.424444444444445e-06, |
| "loss": 2.9914, |
| "mean_token_accuracy": 0.9407924722880125, |
| "num_tokens": 47658392.0, |
| "step": 5760 |
| }, |
| { |
| "entropy": 0.19854985740967096, |
| "epoch": 2.308, |
| "grad_norm": 51.25, |
| "learning_rate": 9.402222222222222e-06, |
| "loss": 3.2477, |
| "mean_token_accuracy": 0.9358540803194046, |
| "num_tokens": 47742655.0, |
| "step": 5770 |
| }, |
| { |
| "entropy": 0.2093534952495247, |
| "epoch": 2.312, |
| "grad_norm": 43.75, |
| "learning_rate": 9.38e-06, |
| "loss": 3.3542, |
| "mean_token_accuracy": 0.9344162929803133, |
| "num_tokens": 47827802.0, |
| "step": 5780 |
| }, |
| { |
| "entropy": 0.2062529031187296, |
| "epoch": 2.316, |
| "grad_norm": 48.25, |
| "learning_rate": 9.35777777777778e-06, |
| "loss": 3.2809, |
| "mean_token_accuracy": 0.9353579673916101, |
| "num_tokens": 47908625.0, |
| "step": 5790 |
| }, |
| { |
| "entropy": 0.19415288937743752, |
| "epoch": 2.32, |
| "grad_norm": 53.25, |
| "learning_rate": 9.335555555555557e-06, |
| "loss": 3.0901, |
| "mean_token_accuracy": 0.9379107497632504, |
| "num_tokens": 47995015.0, |
| "step": 5800 |
| }, |
| { |
| "epoch": 2.32, |
| "eval_chemistry_entropy": 0.39470662355422975, |
| "eval_chemistry_loss": 0.7899705171585083, |
| "eval_chemistry_mean_token_accuracy": 0.8071958431005478, |
| "eval_chemistry_num_tokens": 47995015.0, |
| "eval_chemistry_runtime": 53.6444, |
| "eval_chemistry_samples_per_second": 9.321, |
| "eval_chemistry_steps_per_second": 9.321, |
| "step": 5800 |
| }, |
| { |
| "epoch": 2.32, |
| "eval_physics_entropy": 0.3849036909639835, |
| "eval_physics_loss": 0.65633624792099, |
| "eval_physics_mean_token_accuracy": 0.8284591092467308, |
| "eval_physics_num_tokens": 47995015.0, |
| "eval_physics_runtime": 62.3598, |
| "eval_physics_samples_per_second": 8.018, |
| "eval_physics_steps_per_second": 8.018, |
| "step": 5800 |
| }, |
| { |
| "entropy": 0.19207124339882284, |
| "epoch": 2.324, |
| "grad_norm": 59.25, |
| "learning_rate": 9.313333333333335e-06, |
| "loss": 3.0789, |
| "mean_token_accuracy": 0.9400491904467344, |
| "num_tokens": 48078584.0, |
| "step": 5810 |
| }, |
| { |
| "entropy": 0.1874732781201601, |
| "epoch": 2.328, |
| "grad_norm": 51.5, |
| "learning_rate": 9.291111111111112e-06, |
| "loss": 2.9617, |
| "mean_token_accuracy": 0.9406363628804684, |
| "num_tokens": 48163933.0, |
| "step": 5820 |
| }, |
| { |
| "entropy": 0.202512454520911, |
| "epoch": 2.332, |
| "grad_norm": 55.5, |
| "learning_rate": 9.26888888888889e-06, |
| "loss": 3.2603, |
| "mean_token_accuracy": 0.9366499200463295, |
| "num_tokens": 48251298.0, |
| "step": 5830 |
| }, |
| { |
| "entropy": 0.20060346848331392, |
| "epoch": 2.336, |
| "grad_norm": 71.5, |
| "learning_rate": 9.246666666666667e-06, |
| "loss": 3.2006, |
| "mean_token_accuracy": 0.9366799276322126, |
| "num_tokens": 48336708.0, |
| "step": 5840 |
| }, |
| { |
| "entropy": 0.18084419274237007, |
| "epoch": 2.34, |
| "grad_norm": 47.75, |
| "learning_rate": 9.224444444444445e-06, |
| "loss": 2.8636, |
| "mean_token_accuracy": 0.9434659101068974, |
| "num_tokens": 48420786.0, |
| "step": 5850 |
| }, |
| { |
| "entropy": 0.19163171499967574, |
| "epoch": 2.344, |
| "grad_norm": 44.25, |
| "learning_rate": 9.202222222222224e-06, |
| "loss": 3.0004, |
| "mean_token_accuracy": 0.9406759556382894, |
| "num_tokens": 48501684.0, |
| "step": 5860 |
| }, |
| { |
| "entropy": 0.19346833657473325, |
| "epoch": 2.348, |
| "grad_norm": 77.0, |
| "learning_rate": 9.180000000000002e-06, |
| "loss": 3.1004, |
| "mean_token_accuracy": 0.9387925416231155, |
| "num_tokens": 48583449.0, |
| "step": 5870 |
| }, |
| { |
| "entropy": 0.18264342558104546, |
| "epoch": 2.352, |
| "grad_norm": 62.5, |
| "learning_rate": 9.15777777777778e-06, |
| "loss": 2.9199, |
| "mean_token_accuracy": 0.9425822209566832, |
| "num_tokens": 48665311.0, |
| "step": 5880 |
| }, |
| { |
| "entropy": 0.20894327545538544, |
| "epoch": 2.356, |
| "grad_norm": 45.25, |
| "learning_rate": 9.135555555555557e-06, |
| "loss": 3.361, |
| "mean_token_accuracy": 0.9344129908829928, |
| "num_tokens": 48753861.0, |
| "step": 5890 |
| }, |
| { |
| "entropy": 0.19564867338631303, |
| "epoch": 2.36, |
| "grad_norm": 59.5, |
| "learning_rate": 9.113333333333335e-06, |
| "loss": 3.1121, |
| "mean_token_accuracy": 0.9393926940858364, |
| "num_tokens": 48842066.0, |
| "step": 5900 |
| }, |
| { |
| "epoch": 2.36, |
| "eval_chemistry_entropy": 0.3913639240264893, |
| "eval_chemistry_loss": 0.7933480739593506, |
| "eval_chemistry_mean_token_accuracy": 0.8076732790470124, |
| "eval_chemistry_num_tokens": 48842066.0, |
| "eval_chemistry_runtime": 53.637, |
| "eval_chemistry_samples_per_second": 9.322, |
| "eval_chemistry_steps_per_second": 9.322, |
| "step": 5900 |
| }, |
| { |
| "epoch": 2.36, |
| "eval_physics_entropy": 0.38312798050045965, |
| "eval_physics_loss": 0.6580366492271423, |
| "eval_physics_mean_token_accuracy": 0.8283037160038949, |
| "eval_physics_num_tokens": 48842066.0, |
| "eval_physics_runtime": 62.3358, |
| "eval_physics_samples_per_second": 8.021, |
| "eval_physics_steps_per_second": 8.021, |
| "step": 5900 |
| }, |
| { |
| "entropy": 0.18991808039136232, |
| "epoch": 2.364, |
| "grad_norm": 48.75, |
| "learning_rate": 9.091111111111112e-06, |
| "loss": 2.9892, |
| "mean_token_accuracy": 0.9419933516532183, |
| "num_tokens": 48924724.0, |
| "step": 5910 |
| }, |
| { |
| "entropy": 0.2007227463182062, |
| "epoch": 2.368, |
| "grad_norm": 51.25, |
| "learning_rate": 9.06888888888889e-06, |
| "loss": 3.277, |
| "mean_token_accuracy": 0.9373730711638928, |
| "num_tokens": 49005334.0, |
| "step": 5920 |
| }, |
| { |
| "entropy": 0.19522760221734642, |
| "epoch": 2.372, |
| "grad_norm": 63.75, |
| "learning_rate": 9.046666666666668e-06, |
| "loss": 3.1662, |
| "mean_token_accuracy": 0.9381731398403644, |
| "num_tokens": 49086381.0, |
| "step": 5930 |
| }, |
| { |
| "entropy": 0.19688663026317954, |
| "epoch": 2.376, |
| "grad_norm": 43.0, |
| "learning_rate": 9.024444444444445e-06, |
| "loss": 3.1226, |
| "mean_token_accuracy": 0.9393897090107203, |
| "num_tokens": 49166287.0, |
| "step": 5940 |
| }, |
| { |
| "entropy": 0.2026588932145387, |
| "epoch": 2.38, |
| "grad_norm": 54.0, |
| "learning_rate": 9.002222222222223e-06, |
| "loss": 3.2199, |
| "mean_token_accuracy": 0.9370492726564408, |
| "num_tokens": 49251686.0, |
| "step": 5950 |
| }, |
| { |
| "entropy": 0.1876268893945962, |
| "epoch": 2.384, |
| "grad_norm": 58.0, |
| "learning_rate": 8.98e-06, |
| "loss": 2.9421, |
| "mean_token_accuracy": 0.9418988361954689, |
| "num_tokens": 49331936.0, |
| "step": 5960 |
| }, |
| { |
| "entropy": 0.196075351908803, |
| "epoch": 2.388, |
| "grad_norm": 46.25, |
| "learning_rate": 8.957777777777778e-06, |
| "loss": 3.2015, |
| "mean_token_accuracy": 0.9369890756905079, |
| "num_tokens": 49415465.0, |
| "step": 5970 |
| }, |
| { |
| "entropy": 0.19922029618173837, |
| "epoch": 2.392, |
| "grad_norm": 56.5, |
| "learning_rate": 8.935555555555556e-06, |
| "loss": 3.1737, |
| "mean_token_accuracy": 0.9385156963020563, |
| "num_tokens": 49500119.0, |
| "step": 5980 |
| }, |
| { |
| "entropy": 0.2094525044085458, |
| "epoch": 2.396, |
| "grad_norm": 47.25, |
| "learning_rate": 8.913333333333333e-06, |
| "loss": 3.2756, |
| "mean_token_accuracy": 0.9347373116761446, |
| "num_tokens": 49590052.0, |
| "step": 5990 |
| }, |
| { |
| "entropy": 0.19299745629541576, |
| "epoch": 2.4, |
| "grad_norm": 48.25, |
| "learning_rate": 8.891111111111111e-06, |
| "loss": 3.1099, |
| "mean_token_accuracy": 0.9393123656511306, |
| "num_tokens": 49671048.0, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_chemistry_entropy": 0.3838026507794857, |
| "eval_chemistry_loss": 0.8016492128372192, |
| "eval_chemistry_mean_token_accuracy": 0.8075907635688782, |
| "eval_chemistry_num_tokens": 49671048.0, |
| "eval_chemistry_runtime": 53.5069, |
| "eval_chemistry_samples_per_second": 9.345, |
| "eval_chemistry_steps_per_second": 9.345, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_physics_entropy": 0.3768892270028591, |
| "eval_physics_loss": 0.6634106636047363, |
| "eval_physics_mean_token_accuracy": 0.8284309452176094, |
| "eval_physics_num_tokens": 49671048.0, |
| "eval_physics_runtime": 62.3362, |
| "eval_physics_samples_per_second": 8.021, |
| "eval_physics_steps_per_second": 8.021, |
| "step": 6000 |
| } |
| ], |
| "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": 3.3306606504745165e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
