{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.954990215264188,
  "eval_steps": 500,
  "global_step": 189,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15655577299412915,
      "grad_norm": 8.653885841369629,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 22.3789,
      "step": 10
    },
    {
      "epoch": 0.3131115459882583,
      "grad_norm": 4.433068752288818,
      "learning_rate": 2.9823529411764707e-05,
      "loss": 20.8804,
      "step": 20
    },
    {
      "epoch": 0.46966731898238745,
      "grad_norm": 4.180165767669678,
      "learning_rate": 2.8058823529411766e-05,
      "loss": 19.2313,
      "step": 30
    },
    {
      "epoch": 0.6262230919765166,
      "grad_norm": 4.197498321533203,
      "learning_rate": 2.6294117647058825e-05,
      "loss": 18.3825,
      "step": 40
    },
    {
      "epoch": 0.7827788649706457,
      "grad_norm": 4.2604594230651855,
      "learning_rate": 2.452941176470588e-05,
      "loss": 17.0293,
      "step": 50
    },
    {
      "epoch": 0.9393346379647749,
      "grad_norm": 4.613166809082031,
      "learning_rate": 2.276470588235294e-05,
      "loss": 15.8548,
      "step": 60
    },
    {
      "epoch": 1.0939334637964775,
      "grad_norm": 4.805100917816162,
      "learning_rate": 2.1e-05,
      "loss": 15.2336,
      "step": 70
    },
    {
      "epoch": 1.2504892367906066,
      "grad_norm": 4.5222883224487305,
      "learning_rate": 1.923529411764706e-05,
      "loss": 15.19,
      "step": 80
    },
    {
      "epoch": 1.4070450097847358,
      "grad_norm": 5.12910795211792,
      "learning_rate": 1.747058823529412e-05,
      "loss": 15.0824,
      "step": 90
    },
    {
      "epoch": 1.563600782778865,
      "grad_norm": 5.300595283508301,
      "learning_rate": 1.570588235294118e-05,
      "loss": 14.5899,
      "step": 100
    },
    {
      "epoch": 1.720156555772994,
      "grad_norm": 5.652774333953857,
      "learning_rate": 1.3941176470588236e-05,
      "loss": 15.0659,
      "step": 110
    },
    {
      "epoch": 1.8767123287671232,
      "grad_norm": 5.436872959136963,
      "learning_rate": 1.2176470588235294e-05,
      "loss": 14.7455,
      "step": 120
    },
    {
      "epoch": 2.031311154598826,
      "grad_norm": 5.51776123046875,
      "learning_rate": 1.0411764705882353e-05,
      "loss": 14.5675,
      "step": 130
    },
    {
      "epoch": 2.187866927592955,
      "grad_norm": 5.708178997039795,
      "learning_rate": 8.647058823529412e-06,
      "loss": 14.0757,
      "step": 140
    },
    {
      "epoch": 2.344422700587084,
      "grad_norm": 5.40604829788208,
      "learning_rate": 6.882352941176471e-06,
      "loss": 13.899,
      "step": 150
    },
    {
      "epoch": 2.5009784735812133,
      "grad_norm": 5.536667823791504,
      "learning_rate": 5.11764705882353e-06,
      "loss": 14.1072,
      "step": 160
    },
    {
      "epoch": 2.6575342465753424,
      "grad_norm": 5.577488422393799,
      "learning_rate": 3.3529411764705886e-06,
      "loss": 14.3544,
      "step": 170
    },
    {
      "epoch": 2.8140900195694716,
      "grad_norm": 6.25947380065918,
      "learning_rate": 1.5882352941176472e-06,
      "loss": 13.7119,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 189,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.535639329417011e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}