{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2,
  "eval_steps": 100,
  "global_step": 500,
  "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
    }
  ],
  "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": 2.7900771999920582e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}