{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9987257088244665,
  "eval_steps": 1569,
  "global_step": 6276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24976107040458745,
      "grad_norm": 3.5836572647094727,
      "learning_rate": 2.4984066284257492e-06,
      "loss": 3.2128,
      "step": 392
    },
    {
      "epoch": 0.4995221408091749,
      "grad_norm": 3.5956788063049316,
      "learning_rate": 4.9968132568514985e-06,
      "loss": 2.232,
      "step": 784
    },
    {
      "epoch": 0.7492832112137623,
      "grad_norm": 5.461869239807129,
      "learning_rate": 7.495219885277247e-06,
      "loss": 1.8585,
      "step": 1176
    },
    {
      "epoch": 0.9990442816183498,
      "grad_norm": 4.789157390594482,
      "learning_rate": 9.993626513702997e-06,
      "loss": 1.663,
      "step": 1568
    },
    {
      "epoch": 1.2488053520229372,
      "grad_norm": 3.923671245574951,
      "learning_rate": 9.37719018795795e-06,
      "loss": 1.5195,
      "step": 1960
    },
    {
      "epoch": 1.4985664224275248,
      "grad_norm": 4.947878360748291,
      "learning_rate": 8.75278751194648e-06,
      "loss": 1.481,
      "step": 2352
    },
    {
      "epoch": 1.7483274928321122,
      "grad_norm": 3.5249428749084473,
      "learning_rate": 8.128384835935011e-06,
      "loss": 1.4036,
      "step": 2744
    },
    {
      "epoch": 1.9980885632366996,
      "grad_norm": 1.927209734916687,
      "learning_rate": 7.503982159923543e-06,
      "loss": 1.3675,
      "step": 3136
    },
    {
      "epoch": 2.247849633641287,
      "grad_norm": 5.133701324462891,
      "learning_rate": 6.8795794839120745e-06,
      "loss": 1.2484,
      "step": 3528
    },
    {
      "epoch": 2.4976107040458744,
      "grad_norm": 5.654458045959473,
      "learning_rate": 6.255176807900606e-06,
      "loss": 1.1997,
      "step": 3920
    },
    {
      "epoch": 2.7473717744504618,
      "grad_norm": 7.116914749145508,
      "learning_rate": 5.630774131889137e-06,
      "loss": 1.2026,
      "step": 4312
    },
    {
      "epoch": 2.9971328448550496,
      "grad_norm": 5.798983573913574,
      "learning_rate": 5.006371455877669e-06,
      "loss": 1.1859,
      "step": 4704
    },
    {
      "epoch": 3.246893915259637,
      "grad_norm": 5.535274505615234,
      "learning_rate": 4.3819687798662e-06,
      "loss": 1.0458,
      "step": 5096
    },
    {
      "epoch": 3.4966549856642244,
      "grad_norm": 5.662832736968994,
      "learning_rate": 3.757566103854731e-06,
      "loss": 1.0485,
      "step": 5488
    },
    {
      "epoch": 3.746416056068812,
      "grad_norm": 5.849664211273193,
      "learning_rate": 3.1331634278432627e-06,
      "loss": 1.0564,
      "step": 5880
    },
    {
      "epoch": 3.996177126473399,
      "grad_norm": 6.500792026519775,
      "learning_rate": 2.5087607518317936e-06,
      "loss": 1.0403,
      "step": 6272
    }
  ],
  "logging_steps": 392,
  "max_steps": 7847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 1569,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}