{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 162,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.4490234375,
      "epoch": 0.18518518518518517,
      "grad_norm": 1.605711817741394,
      "learning_rate": 0.00019997919281892067,
      "loss": 2.744666862487793,
      "mean_token_accuracy": 0.4455879807472229,
      "num_tokens": 35176.0,
      "step": 10
    },
    {
      "entropy": 2.14208984375,
      "epoch": 0.37037037037037035,
      "grad_norm": 1.9346004724502563,
      "learning_rate": 0.00019749279121818235,
      "loss": 1.9460367202758788,
      "mean_token_accuracy": 0.5691858988255263,
      "num_tokens": 70631.0,
      "step": 20
    },
    {
      "entropy": 1.50927734375,
      "epoch": 0.5555555555555556,
      "grad_norm": 0.859683096408844,
      "learning_rate": 0.00019096319953545185,
      "loss": 1.5292683601379395,
      "mean_token_accuracy": 0.6657284118235112,
      "num_tokens": 106615.0,
      "step": 30
    },
    {
      "entropy": 1.45556640625,
      "epoch": 0.7407407407407407,
      "grad_norm": 0.7568148970603943,
      "learning_rate": 0.000180661210923753,
      "loss": 1.4439837455749511,
      "mean_token_accuracy": 0.6813905350863934,
      "num_tokens": 142274.0,
      "step": 40
    },
    {
      "entropy": 1.4376953125,
      "epoch": 0.9259259259259259,
      "grad_norm": 0.7695605158805847,
      "learning_rate": 0.00016701406618375596,
      "loss": 1.434541606903076,
      "mean_token_accuracy": 0.6835584975779057,
      "num_tokens": 177779.0,
      "step": 50
    },
    {
      "entropy": 1.4240234375,
      "epoch": 1.1111111111111112,
      "grad_norm": 0.7485360503196716,
      "learning_rate": 0.00015058773536894685,
      "loss": 1.398463821411133,
      "mean_token_accuracy": 0.6880027234554291,
      "num_tokens": 213250.0,
      "step": 60
    },
    {
      "entropy": 1.3787109375,
      "epoch": 1.2962962962962963,
      "grad_norm": 0.8382265567779541,
      "learning_rate": 0.00013206344605527355,
      "loss": 1.3820528030395507,
      "mean_token_accuracy": 0.6910028986632824,
      "num_tokens": 249008.0,
      "step": 70
    },
    {
      "entropy": 1.39111328125,
      "epoch": 1.4814814814814814,
      "grad_norm": 0.8756011128425598,
      "learning_rate": 0.000112209431687416,
      "loss": 1.3737930297851562,
      "mean_token_accuracy": 0.6952961266040802,
      "num_tokens": 284762.0,
      "step": 80
    },
    {
      "entropy": 1.3533203125,
      "epoch": 1.6666666666666665,
      "grad_norm": 0.8062230348587036,
      "learning_rate": 9.184907164529368e-05,
      "loss": 1.3459887504577637,
      "mean_token_accuracy": 0.6956925392150879,
      "num_tokens": 320323.0,
      "step": 90
    },
    {
      "entropy": 1.3333984375,
      "epoch": 1.8518518518518519,
      "grad_norm": 0.7905425429344177,
      "learning_rate": 7.182674431585704e-05,
      "loss": 1.3476751327514649,
      "mean_token_accuracy": 0.6990618519484997,
      "num_tokens": 355791.0,
      "step": 100
    },
    {
      "entropy": 1.35595703125,
      "epoch": 2.037037037037037,
      "grad_norm": 0.8151571154594421,
      "learning_rate": 5.297280930072632e-05,
      "loss": 1.3445645332336427,
      "mean_token_accuracy": 0.6957452893257141,
      "num_tokens": 391407.0,
      "step": 110
    },
    {
      "entropy": 1.36494140625,
      "epoch": 2.2222222222222223,
      "grad_norm": 0.77378249168396,
      "learning_rate": 3.606917100644487e-05,
      "loss": 1.3390249252319335,
      "mean_token_accuracy": 0.698172252625227,
      "num_tokens": 427190.0,
      "step": 120
    },
    {
      "entropy": 1.342578125,
      "epoch": 2.4074074074074074,
      "grad_norm": 0.893750786781311,
      "learning_rate": 2.1816851753197032e-05,
      "loss": 1.322931671142578,
      "mean_token_accuracy": 0.6984936438500882,
      "num_tokens": 462696.0,
      "step": 130
    },
    {
      "entropy": 1.339453125,
      "epoch": 2.5925925925925926,
      "grad_norm": 0.82007896900177,
      "learning_rate": 1.0806919199730615e-05,
      "loss": 1.3379673957824707,
      "mean_token_accuracy": 0.702365966886282,
      "num_tokens": 498412.0,
      "step": 140
    },
    {
      "entropy": 1.33486328125,
      "epoch": 2.7777777777777777,
      "grad_norm": 0.8532996773719788,
      "learning_rate": 3.495973773086014e-06,
      "loss": 1.3067991256713867,
      "mean_token_accuracy": 0.701677817851305,
      "num_tokens": 533710.0,
      "step": 150
    },
    {
      "entropy": 1.347265625,
      "epoch": 2.962962962962963,
      "grad_norm": 0.8509896397590637,
      "learning_rate": 1.8721268066330676e-07,
      "loss": 1.3350863456726074,
      "mean_token_accuracy": 0.7003593638539314,
      "num_tokens": 569320.0,
      "step": 160
    }
  ],
  "logging_steps": 10,
  "max_steps": 162,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1796759427633408.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}