| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 100, |
| "global_step": 2500, |
| "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 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 10000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3871405343990067e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
