{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10700909577314072,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005350454788657035,
      "eval_loss": 1.297796368598938,
      "eval_runtime": 38.1253,
      "eval_samples_per_second": 20.642,
      "eval_steps_per_second": 10.334,
      "step": 1
    },
    {
      "epoch": 0.005350454788657036,
      "grad_norm": 0.6613432765007019,
      "learning_rate": 0.0002,
      "loss": 1.2012,
      "step": 10
    },
    {
      "epoch": 0.010700909577314071,
      "grad_norm": 0.7662879228591919,
      "learning_rate": 0.0002,
      "loss": 1.0476,
      "step": 20
    },
    {
      "epoch": 0.016051364365971106,
      "grad_norm": 0.6839860081672668,
      "learning_rate": 0.0002,
      "loss": 0.9515,
      "step": 30
    },
    {
      "epoch": 0.021401819154628143,
      "grad_norm": 0.543673038482666,
      "learning_rate": 0.0002,
      "loss": 0.9613,
      "step": 40
    },
    {
      "epoch": 0.02675227394328518,
      "grad_norm": 0.5917090177536011,
      "learning_rate": 0.0002,
      "loss": 0.8927,
      "step": 50
    },
    {
      "epoch": 0.02675227394328518,
      "eval_loss": 0.9101773500442505,
      "eval_runtime": 37.1703,
      "eval_samples_per_second": 21.173,
      "eval_steps_per_second": 10.6,
      "step": 50
    },
    {
      "epoch": 0.03210272873194221,
      "grad_norm": 0.5942009687423706,
      "learning_rate": 0.0002,
      "loss": 0.9291,
      "step": 60
    },
    {
      "epoch": 0.03745318352059925,
      "grad_norm": 0.6650110483169556,
      "learning_rate": 0.0002,
      "loss": 0.8859,
      "step": 70
    },
    {
      "epoch": 0.042803638309256285,
      "grad_norm": 0.5931994318962097,
      "learning_rate": 0.0002,
      "loss": 0.9061,
      "step": 80
    },
    {
      "epoch": 0.048154093097913325,
      "grad_norm": 0.6303430795669556,
      "learning_rate": 0.0002,
      "loss": 0.8647,
      "step": 90
    },
    {
      "epoch": 0.05350454788657036,
      "grad_norm": 0.613747775554657,
      "learning_rate": 0.0002,
      "loss": 0.9061,
      "step": 100
    },
    {
      "epoch": 0.05350454788657036,
      "eval_loss": 0.8843422532081604,
      "eval_runtime": 37.185,
      "eval_samples_per_second": 21.164,
      "eval_steps_per_second": 10.596,
      "step": 100
    },
    {
      "epoch": 0.05885500267522739,
      "grad_norm": 0.5722771883010864,
      "learning_rate": 0.0002,
      "loss": 0.9267,
      "step": 110
    },
    {
      "epoch": 0.06420545746388442,
      "grad_norm": 0.5415870547294617,
      "learning_rate": 0.0002,
      "loss": 0.9077,
      "step": 120
    },
    {
      "epoch": 0.06955591225254147,
      "grad_norm": 0.5300649404525757,
      "learning_rate": 0.0002,
      "loss": 0.8924,
      "step": 130
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": 0.5958105325698853,
      "learning_rate": 0.0002,
      "loss": 0.9126,
      "step": 140
    },
    {
      "epoch": 0.08025682182985554,
      "grad_norm": 0.5649930238723755,
      "learning_rate": 0.0002,
      "loss": 0.8239,
      "step": 150
    },
    {
      "epoch": 0.08025682182985554,
      "eval_loss": 0.8727919459342957,
      "eval_runtime": 37.1914,
      "eval_samples_per_second": 21.161,
      "eval_steps_per_second": 10.594,
      "step": 150
    },
    {
      "epoch": 0.08560727661851257,
      "grad_norm": 0.665091335773468,
      "learning_rate": 0.0002,
      "loss": 0.9073,
      "step": 160
    },
    {
      "epoch": 0.0909577314071696,
      "grad_norm": 0.5974867343902588,
      "learning_rate": 0.0002,
      "loss": 0.8846,
      "step": 170
    },
    {
      "epoch": 0.09630818619582665,
      "grad_norm": 0.5943084359169006,
      "learning_rate": 0.0002,
      "loss": 0.8716,
      "step": 180
    },
    {
      "epoch": 0.10165864098448368,
      "grad_norm": 0.595061182975769,
      "learning_rate": 0.0002,
      "loss": 0.8635,
      "step": 190
    },
    {
      "epoch": 0.10700909577314072,
      "grad_norm": 0.575626790523529,
      "learning_rate": 0.0002,
      "loss": 0.8597,
      "step": 200
    },
    {
      "epoch": 0.10700909577314072,
      "eval_loss": 0.8620458245277405,
      "eval_runtime": 37.2066,
      "eval_samples_per_second": 21.152,
      "eval_steps_per_second": 10.59,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.3324083453952e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}