{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4106776180698152,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.9327721463143825,
      "epoch": 0.02053388090349076,
      "grad_norm": 0.1806640625,
      "learning_rate": 0.00012972972972972974,
      "loss": 0.9855536651611329,
      "mean_token_accuracy": 0.7679368060827255,
      "num_tokens": 201640.0,
      "step": 25
    },
    {
      "entropy": 0.8724879887700081,
      "epoch": 0.04106776180698152,
      "grad_norm": 0.1474609375,
      "learning_rate": 0.00019994905570360817,
      "loss": 0.8708956909179687,
      "mean_token_accuracy": 0.7903838059306145,
      "num_tokens": 404792.0,
      "step": 50
    },
    {
      "entropy": 0.8544691229611635,
      "epoch": 0.061601642710472276,
      "grad_norm": 0.15234375,
      "learning_rate": 0.00019951602516690988,
      "loss": 0.8482267761230469,
      "mean_token_accuracy": 0.7932471469044685,
      "num_tokens": 606810.0,
      "step": 75
    },
    {
      "entropy": 0.8944924513995648,
      "epoch": 0.08213552361396304,
      "grad_norm": 0.1640625,
      "learning_rate": 0.0001986430349043317,
      "loss": 0.8818518829345703,
      "mean_token_accuracy": 0.7834139719605446,
      "num_tokens": 807549.0,
      "step": 100
    },
    {
      "entropy": 0.9099837489426136,
      "epoch": 0.1026694045174538,
      "grad_norm": 0.14453125,
      "learning_rate": 0.0001973339444003735,
      "loss": 0.8984813690185547,
      "mean_token_accuracy": 0.7812782523036003,
      "num_tokens": 1008223.0,
      "step": 125
    },
    {
      "entropy": 0.8356300877034664,
      "epoch": 0.12320328542094455,
      "grad_norm": 0.15234375,
      "learning_rate": 0.0001955945411359792,
      "loss": 0.8289723205566406,
      "mean_token_accuracy": 0.7977875503897667,
      "num_tokens": 1209811.0,
      "step": 150
    },
    {
      "entropy": 0.8626699298620224,
      "epoch": 0.1437371663244353,
      "grad_norm": 0.150390625,
      "learning_rate": 0.00019343251500211975,
      "loss": 0.8522069549560547,
      "mean_token_accuracy": 0.789976358115673,
      "num_tokens": 1411353.0,
      "step": 175
    },
    {
      "entropy": 0.8640103512257338,
      "epoch": 0.16427104722792607,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.00019085742430283322,
      "loss": 0.8584527587890625,
      "mean_token_accuracy": 0.7891600033640862,
      "num_tokens": 1614555.0,
      "step": 200
    },
    {
      "entropy": 0.8809252215921879,
      "epoch": 0.18480492813141683,
      "grad_norm": 0.1640625,
      "learning_rate": 0.0001878806534980221,
      "loss": 0.87360107421875,
      "mean_token_accuracy": 0.7867547670006751,
      "num_tokens": 1816672.0,
      "step": 225
    },
    {
      "entropy": 0.8541410507261753,
      "epoch": 0.2053388090349076,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.0001845153628728274,
      "loss": 0.8500338745117187,
      "mean_token_accuracy": 0.7926329699158668,
      "num_tokens": 2018500.0,
      "step": 250
    },
    {
      "entropy": 0.8946534705162048,
      "epoch": 0.22587268993839835,
      "grad_norm": 0.1689453125,
      "learning_rate": 0.00018077643035609004,
      "loss": 0.8828852844238281,
      "mean_token_accuracy": 0.7846844819188118,
      "num_tokens": 2220866.0,
      "step": 275
    },
    {
      "entropy": 0.8587514898180961,
      "epoch": 0.2464065708418891,
      "grad_norm": 0.171875,
      "learning_rate": 0.0001766803857451204,
      "loss": 0.8391613006591797,
      "mean_token_accuracy": 0.7931238517165184,
      "num_tokens": 2421013.0,
      "step": 300
    },
    {
      "entropy": 0.876440706178546,
      "epoch": 0.2669404517453799,
      "grad_norm": 0.1796875,
      "learning_rate": 0.00017224533762756776,
      "loss": 0.8661175537109375,
      "mean_token_accuracy": 0.7875098848342895,
      "num_tokens": 2623081.0,
      "step": 325
    },
    {
      "entropy": 0.8844135162234307,
      "epoch": 0.2874743326488706,
      "grad_norm": 0.15234375,
      "learning_rate": 0.00016749089332346713,
      "loss": 0.8735830688476562,
      "mean_token_accuracy": 0.7862337788939476,
      "num_tokens": 2824382.0,
      "step": 350
    },
    {
      "entropy": 0.7987543179094792,
      "epoch": 0.3080082135523614,
      "grad_norm": 0.154296875,
      "learning_rate": 0.00016243807220139988,
      "loss": 0.79259033203125,
      "mean_token_accuracy": 0.804975683093071,
      "num_tokens": 3026700.0,
      "step": 375
    },
    {
      "entropy": 0.8895229130983353,
      "epoch": 0.32854209445585214,
      "grad_norm": 0.171875,
      "learning_rate": 0.0001571092127519967,
      "loss": 0.8765971374511718,
      "mean_token_accuracy": 0.7862004506587982,
      "num_tokens": 3228741.0,
      "step": 400
    },
    {
      "entropy": 0.8609522663801908,
      "epoch": 0.3490759753593429,
      "grad_norm": 0.1484375,
      "learning_rate": 0.00015152787382960968,
      "loss": 0.8444467163085938,
      "mean_token_accuracy": 0.793184621334076,
      "num_tokens": 3428336.0,
      "step": 425
    },
    {
      "entropy": 0.8780751578509808,
      "epoch": 0.36960985626283366,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0001457187304987645,
      "loss": 0.8594348907470704,
      "mean_token_accuracy": 0.7891285745799541,
      "num_tokens": 3626721.0,
      "step": 450
    },
    {
      "entropy": 0.815336870700121,
      "epoch": 0.39014373716632444,
      "grad_norm": 0.1357421875,
      "learning_rate": 0.0001397074649458544,
      "loss": 0.8068878936767578,
      "mean_token_accuracy": 0.8028223878145218,
      "num_tokens": 3829062.0,
      "step": 475
    },
    {
      "entropy": 0.8639824625849724,
      "epoch": 0.4106776180698152,
      "grad_norm": 0.169921875,
      "learning_rate": 0.00013352065293835397,
      "loss": 0.8533393096923828,
      "mean_token_accuracy": 0.7899997106194496,
      "num_tokens": 4030678.0,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 1218,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.400347382112133e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}