{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 199,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.0732421875,
      "epoch": 0.005044136191677175,
      "grad_norm": 3.729904548791402,
      "learning_rate": 0.0,
      "loss": 1.5705682039260864,
      "mean_token_accuracy": 0.5984444469213486,
      "num_tokens": 397809.0,
      "step": 1
    },
    {
      "entropy": 1.140625,
      "epoch": 0.025220680958385876,
      "grad_norm": 3.537819920462687,
      "learning_rate": 1.295370924755994e-05,
      "loss": 1.569430947303772,
      "mean_token_accuracy": 0.5931065641343594,
      "num_tokens": 1792332.0,
      "step": 5
    },
    {
      "entropy": 1.28984375,
      "epoch": 0.05044136191677175,
      "grad_norm": 1.9953551967058947,
      "learning_rate": 1.853256816058254e-05,
      "loss": 1.4315099716186523,
      "mean_token_accuracy": 0.6139604687690735,
      "num_tokens": 3573398.0,
      "step": 10
    },
    {
      "entropy": 1.2671875,
      "epoch": 0.07566204287515763,
      "grad_norm": 2.0123345607376537,
      "learning_rate": 1.989637305699482e-05,
      "loss": 1.303097915649414,
      "mean_token_accuracy": 0.6386384278535843,
      "num_tokens": 5352795.0,
      "step": 15
    },
    {
      "entropy": 1.34296875,
      "epoch": 0.1008827238335435,
      "grad_norm": 2.3429686709929016,
      "learning_rate": 1.9637305699481867e-05,
      "loss": 1.2593023300170898,
      "mean_token_accuracy": 0.646000188589096,
      "num_tokens": 7129865.0,
      "step": 20
    },
    {
      "entropy": 1.2890625,
      "epoch": 0.12610340479192939,
      "grad_norm": 2.093171715611346,
      "learning_rate": 1.9378238341968913e-05,
      "loss": 1.25695743560791,
      "mean_token_accuracy": 0.6471466660499573,
      "num_tokens": 8868732.0,
      "step": 25
    },
    {
      "entropy": 1.315234375,
      "epoch": 0.15132408575031525,
      "grad_norm": 1.5214039865876905,
      "learning_rate": 1.9119170984455958e-05,
      "loss": 1.2165451049804688,
      "mean_token_accuracy": 0.6549518913030624,
      "num_tokens": 10737138.0,
      "step": 30
    },
    {
      "entropy": 1.282421875,
      "epoch": 0.17654476670870115,
      "grad_norm": 1.7720335086338008,
      "learning_rate": 1.8860103626943007e-05,
      "loss": 1.1993481636047363,
      "mean_token_accuracy": 0.657388761639595,
      "num_tokens": 12626963.0,
      "step": 35
    },
    {
      "entropy": 1.2640625,
      "epoch": 0.201765447667087,
      "grad_norm": 1.8352721153566052,
      "learning_rate": 1.8601036269430053e-05,
      "loss": 1.1846282958984375,
      "mean_token_accuracy": 0.6627674549818039,
      "num_tokens": 14433262.0,
      "step": 40
    },
    {
      "entropy": 1.251953125,
      "epoch": 0.22698612862547288,
      "grad_norm": 1.8067651099435984,
      "learning_rate": 1.83419689119171e-05,
      "loss": 1.1756595611572265,
      "mean_token_accuracy": 0.6638763636350632,
      "num_tokens": 16326390.0,
      "step": 45
    },
    {
      "entropy": 1.273046875,
      "epoch": 0.25220680958385877,
      "grad_norm": 3.465628169730638,
      "learning_rate": 1.8082901554404147e-05,
      "loss": 1.1847558975219727,
      "mean_token_accuracy": 0.6604940384626389,
      "num_tokens": 18279034.0,
      "step": 50
    },
    {
      "entropy": 1.25625,
      "epoch": 0.27742749054224464,
      "grad_norm": 1.4054861856544547,
      "learning_rate": 1.7823834196891192e-05,
      "loss": 1.1652128219604492,
      "mean_token_accuracy": 0.6664551287889481,
      "num_tokens": 20208031.0,
      "step": 55
    },
    {
      "entropy": 1.266796875,
      "epoch": 0.3026481715006305,
      "grad_norm": 3.4183832212008456,
      "learning_rate": 1.756476683937824e-05,
      "loss": 1.1770149230957032,
      "mean_token_accuracy": 0.6627189248800278,
      "num_tokens": 21908532.0,
      "step": 60
    },
    {
      "entropy": 1.26484375,
      "epoch": 0.32786885245901637,
      "grad_norm": 3.1555109653499964,
      "learning_rate": 1.7305699481865287e-05,
      "loss": 1.1431950569152831,
      "mean_token_accuracy": 0.6696279108524322,
      "num_tokens": 23700105.0,
      "step": 65
    },
    {
      "entropy": 1.242578125,
      "epoch": 0.3530895334174023,
      "grad_norm": 2.3839995394597286,
      "learning_rate": 1.7046632124352332e-05,
      "loss": 1.1668883323669434,
      "mean_token_accuracy": 0.6657638341188431,
      "num_tokens": 25603944.0,
      "step": 70
    },
    {
      "entropy": 1.24921875,
      "epoch": 0.37831021437578816,
      "grad_norm": 1.8426925035490107,
      "learning_rate": 1.6787564766839378e-05,
      "loss": 1.13353271484375,
      "mean_token_accuracy": 0.6711880832910537,
      "num_tokens": 27318273.0,
      "step": 75
    },
    {
      "entropy": 1.26171875,
      "epoch": 0.403530895334174,
      "grad_norm": 1.9994154023171613,
      "learning_rate": 1.6528497409326427e-05,
      "loss": 1.1364672660827637,
      "mean_token_accuracy": 0.672755679488182,
      "num_tokens": 29158308.0,
      "step": 80
    },
    {
      "entropy": 1.249609375,
      "epoch": 0.4287515762925599,
      "grad_norm": 2.9275771398624597,
      "learning_rate": 1.6269430051813472e-05,
      "loss": 1.121041488647461,
      "mean_token_accuracy": 0.6760148137807847,
      "num_tokens": 30941822.0,
      "step": 85
    },
    {
      "entropy": 1.25390625,
      "epoch": 0.45397225725094575,
      "grad_norm": 1.5615516079216,
      "learning_rate": 1.6010362694300518e-05,
      "loss": 1.1162029266357423,
      "mean_token_accuracy": 0.6768355071544647,
      "num_tokens": 32787654.0,
      "step": 90
    },
    {
      "entropy": 1.254296875,
      "epoch": 0.4791929382093317,
      "grad_norm": 2.8170519799515197,
      "learning_rate": 1.5751295336787566e-05,
      "loss": 1.1182659149169922,
      "mean_token_accuracy": 0.6761424988508224,
      "num_tokens": 34644366.0,
      "step": 95
    },
    {
      "entropy": 1.238671875,
      "epoch": 0.5044136191677175,
      "grad_norm": 2.805028653265598,
      "learning_rate": 1.5492227979274612e-05,
      "loss": 1.1245113372802735,
      "mean_token_accuracy": 0.6737537115812302,
      "num_tokens": 36483579.0,
      "step": 100
    },
    {
      "entropy": 1.226953125,
      "epoch": 0.5296343001261034,
      "grad_norm": 1.438265666554789,
      "learning_rate": 1.523316062176166e-05,
      "loss": 1.1135278701782227,
      "mean_token_accuracy": 0.6800242573022842,
      "num_tokens": 38534892.0,
      "step": 105
    },
    {
      "entropy": 1.240625,
      "epoch": 0.5548549810844893,
      "grad_norm": 6.154593405469548,
      "learning_rate": 1.4974093264248706e-05,
      "loss": 1.127542495727539,
      "mean_token_accuracy": 0.6712189227342605,
      "num_tokens": 40255595.0,
      "step": 110
    },
    {
      "entropy": 1.221875,
      "epoch": 0.5800756620428752,
      "grad_norm": 1.712858492865262,
      "learning_rate": 1.4715025906735752e-05,
      "loss": 1.0767477989196776,
      "mean_token_accuracy": 0.6854143172502518,
      "num_tokens": 42143795.0,
      "step": 115
    },
    {
      "entropy": 1.228125,
      "epoch": 0.605296343001261,
      "grad_norm": 1.7954082649002236,
      "learning_rate": 1.4455958549222799e-05,
      "loss": 1.1128243446350097,
      "mean_token_accuracy": 0.6780534535646439,
      "num_tokens": 44010920.0,
      "step": 120
    },
    {
      "entropy": 1.25,
      "epoch": 0.6305170239596469,
      "grad_norm": 2.557128723303994,
      "learning_rate": 1.4196891191709844e-05,
      "loss": 1.1001087188720704,
      "mean_token_accuracy": 0.6781179249286652,
      "num_tokens": 45633080.0,
      "step": 125
    },
    {
      "entropy": 1.233984375,
      "epoch": 0.6557377049180327,
      "grad_norm": 1.6132918279446875,
      "learning_rate": 1.3937823834196893e-05,
      "loss": 1.0829249382019044,
      "mean_token_accuracy": 0.6852418035268784,
      "num_tokens": 47264233.0,
      "step": 130
    },
    {
      "entropy": 1.2265625,
      "epoch": 0.6809583858764187,
      "grad_norm": 1.35683478183202,
      "learning_rate": 1.3678756476683939e-05,
      "loss": 1.0771641731262207,
      "mean_token_accuracy": 0.6857132732868194,
      "num_tokens": 49137662.0,
      "step": 135
    },
    {
      "entropy": 1.2171875,
      "epoch": 0.7061790668348046,
      "grad_norm": 1.5570774063045756,
      "learning_rate": 1.3419689119170986e-05,
      "loss": 1.0707455635070802,
      "mean_token_accuracy": 0.6857165455818176,
      "num_tokens": 50943509.0,
      "step": 140
    },
    {
      "entropy": 1.248828125,
      "epoch": 0.7313997477931904,
      "grad_norm": 2.8786377018075457,
      "learning_rate": 1.3160621761658033e-05,
      "loss": 1.082810401916504,
      "mean_token_accuracy": 0.6832135945558548,
      "num_tokens": 52697400.0,
      "step": 145
    },
    {
      "entropy": 1.212109375,
      "epoch": 0.7566204287515763,
      "grad_norm": 1.4838869261745697,
      "learning_rate": 1.2901554404145079e-05,
      "loss": 1.055869960784912,
      "mean_token_accuracy": 0.6903243094682694,
      "num_tokens": 54550790.0,
      "step": 150
    },
    {
      "entropy": 1.2265625,
      "epoch": 0.7818411097099621,
      "grad_norm": 1.322651287548672,
      "learning_rate": 1.2642487046632126e-05,
      "loss": 1.0742380142211914,
      "mean_token_accuracy": 0.6852674335241318,
      "num_tokens": 56273458.0,
      "step": 155
    },
    {
      "entropy": 1.2453125,
      "epoch": 0.807061790668348,
      "grad_norm": 8.55404246200832,
      "learning_rate": 1.2383419689119171e-05,
      "loss": 1.0786266326904297,
      "mean_token_accuracy": 0.6855500996112823,
      "num_tokens": 58121056.0,
      "step": 160
    },
    {
      "entropy": 1.203125,
      "epoch": 0.832282471626734,
      "grad_norm": 2.0497153186806325,
      "learning_rate": 1.212435233160622e-05,
      "loss": 1.0652950286865235,
      "mean_token_accuracy": 0.6877057552337646,
      "num_tokens": 60048538.0,
      "step": 165
    },
    {
      "entropy": 1.208203125,
      "epoch": 0.8575031525851198,
      "grad_norm": 1.2643588159534247,
      "learning_rate": 1.1865284974093266e-05,
      "loss": 1.0611819267272948,
      "mean_token_accuracy": 0.6904475122690201,
      "num_tokens": 61835940.0,
      "step": 170
    },
    {
      "entropy": 1.2171875,
      "epoch": 0.8827238335435057,
      "grad_norm": 1.204921091847234,
      "learning_rate": 1.1606217616580311e-05,
      "loss": 1.0413402557373046,
      "mean_token_accuracy": 0.6954286068677902,
      "num_tokens": 63573308.0,
      "step": 175
    },
    {
      "entropy": 1.20078125,
      "epoch": 0.9079445145018915,
      "grad_norm": 1.387043880574625,
      "learning_rate": 1.1347150259067358e-05,
      "loss": 1.049238681793213,
      "mean_token_accuracy": 0.6919074177742004,
      "num_tokens": 65497008.0,
      "step": 180
    },
    {
      "entropy": 1.206640625,
      "epoch": 0.9331651954602774,
      "grad_norm": 1.279478089664614,
      "learning_rate": 1.1088082901554404e-05,
      "loss": 1.0584297180175781,
      "mean_token_accuracy": 0.6892471343278885,
      "num_tokens": 67254338.0,
      "step": 185
    },
    {
      "entropy": 1.2171875,
      "epoch": 0.9583858764186634,
      "grad_norm": 1.5719174306561159,
      "learning_rate": 1.0829015544041453e-05,
      "loss": 1.0455381393432617,
      "mean_token_accuracy": 0.6926654905080796,
      "num_tokens": 69176523.0,
      "step": 190
    },
    {
      "entropy": 1.209375,
      "epoch": 0.9836065573770492,
      "grad_norm": 1.4906711673793527,
      "learning_rate": 1.0569948186528498e-05,
      "loss": 1.0241477966308594,
      "mean_token_accuracy": 0.6976693719625473,
      "num_tokens": 71048975.0,
      "step": 195
    },
    {
      "epoch": 1.0,
      "eval_entropy": 1.2234002976190477,
      "eval_loss": 1.0335501432418823,
      "eval_mean_token_accuracy": 0.6941843855948675,
      "eval_num_tokens": 72109037.0,
      "eval_runtime": 533.6615,
      "eval_samples_per_second": 0.624,
      "eval_steps_per_second": 0.079,
      "step": 199
    }
  ],
  "logging_steps": 5,
  "max_steps": 398,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 940923320795136.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}