| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "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 |
| } |
| ], |
| "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": 5.559510372210398e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
