{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 377,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.5562486915290357,
      "epoch": 0.06635700066357,
      "grad_norm": 0.0184326171875,
      "learning_rate": 0.00019946708199115211,
      "loss": 1.6421920776367187,
      "mean_token_accuracy": 0.6302989659458399,
      "num_tokens": 340197.0,
      "step": 25
    },
    {
      "entropy": 1.2358380392193795,
      "epoch": 0.13271400132714,
      "grad_norm": 0.034912109375,
      "learning_rate": 0.0001949717842791432,
      "loss": 1.1825144958496094,
      "mean_token_accuracy": 0.7164402473717928,
      "num_tokens": 681873.0,
      "step": 50
    },
    {
      "entropy": 0.9332277816906571,
      "epoch": 0.19907100199071,
      "grad_norm": 0.0302734375,
      "learning_rate": 0.00018609610158889942,
      "loss": 0.860277099609375,
      "mean_token_accuracy": 0.7937182428687811,
      "num_tokens": 1025821.0,
      "step": 75
    },
    {
      "entropy": 0.6990280481893569,
      "epoch": 0.26542800265428,
      "grad_norm": 0.033447265625,
      "learning_rate": 0.0001732494071613579,
      "loss": 0.6413444519042969,
      "mean_token_accuracy": 0.8473471283167601,
      "num_tokens": 1363016.0,
      "step": 100
    },
    {
      "entropy": 0.6252105168486014,
      "epoch": 0.33178500331785005,
      "grad_norm": 0.040771484375,
      "learning_rate": 0.00015702422926917872,
      "loss": 0.568554801940918,
      "mean_token_accuracy": 0.8674215438961983,
      "num_tokens": 1708078.0,
      "step": 125
    },
    {
      "entropy": 0.4965320496726781,
      "epoch": 0.39814200398142,
      "grad_norm": 0.03662109375,
      "learning_rate": 0.0001381689220266659,
      "loss": 0.45257919311523437,
      "mean_token_accuracy": 0.8954442175477744,
      "num_tokens": 2046077.0,
      "step": 150
    },
    {
      "entropy": 0.47735783314332364,
      "epoch": 0.46449900464499005,
      "grad_norm": 0.033935546875,
      "learning_rate": 0.00011755314904214284,
      "loss": 0.4485871124267578,
      "mean_token_accuracy": 0.9003452565521002,
      "num_tokens": 2387971.0,
      "step": 175
    },
    {
      "entropy": 0.4234251272957772,
      "epoch": 0.53085600530856,
      "grad_norm": 0.022705078125,
      "learning_rate": 9.612777191078258e-05,
      "loss": 0.3898358535766602,
      "mean_token_accuracy": 0.9132146901637316,
      "num_tokens": 2731004.0,
      "step": 200
    },
    {
      "entropy": 0.512334642924834,
      "epoch": 0.59721300597213,
      "grad_norm": 0.027587890625,
      "learning_rate": 7.48809936115181e-05,
      "loss": 0.48469039916992185,
      "mean_token_accuracy": 0.8931490843743086,
      "num_tokens": 3075845.0,
      "step": 225
    },
    {
      "entropy": 0.4335173129173927,
      "epoch": 0.6635700066357001,
      "grad_norm": 0.0196533203125,
      "learning_rate": 5.479277960676958e-05,
      "loss": 0.4188508987426758,
      "mean_token_accuracy": 0.908899156153202,
      "num_tokens": 3419572.0,
      "step": 250
    },
    {
      "entropy": 0.4149061946058646,
      "epoch": 0.7299270072992701,
      "grad_norm": 0.0157470703125,
      "learning_rate": 3.678965888126513e-05,
      "loss": 0.3769934844970703,
      "mean_token_accuracy": 0.9135672262310982,
      "num_tokens": 3761523.0,
      "step": 275
    },
    {
      "entropy": 0.39260273962281644,
      "epoch": 0.79628400796284,
      "grad_norm": 0.0169677734375,
      "learning_rate": 2.1701989632293717e-05,
      "loss": 0.35523429870605466,
      "mean_token_accuracy": 0.9186709802597761,
      "num_tokens": 4093017.0,
      "step": 300
    },
    {
      "entropy": 0.4600309434533119,
      "epoch": 0.8626410086264101,
      "grad_norm": 0.021240234375,
      "learning_rate": 1.0225660646576629e-05,
      "loss": 0.43257938385009764,
      "mean_token_accuracy": 0.9030144046247005,
      "num_tokens": 4439510.0,
      "step": 325
    },
    {
      "entropy": 0.4613286603335291,
      "epoch": 0.9289980092899801,
      "grad_norm": 0.030517578125,
      "learning_rate": 2.889994811704966e-06,
      "loss": 0.44339012145996093,
      "mean_token_accuracy": 0.9041482334583998,
      "num_tokens": 4784614.0,
      "step": 350
    },
    {
      "entropy": 0.3619327815785073,
      "epoch": 0.9953550099535501,
      "grad_norm": 0.0159912109375,
      "learning_rate": 3.333514894887646e-08,
      "loss": 0.3405461883544922,
      "mean_token_accuracy": 0.9234929252415895,
      "num_tokens": 5127234.0,
      "step": 375
    }
  ],
  "logging_steps": 25,
  "max_steps": 377,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1977274766790246e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}