{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 18.42748838705773,
      "learning_rate": 5e-07,
      "loss": 1.7298,
      "step": 5
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 12.493951998292884,
      "learning_rate": 1e-06,
      "loss": 1.6022,
      "step": 10
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 7.531096485746523,
      "learning_rate": 9.939652198703783e-07,
      "loss": 1.2855,
      "step": 15
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 4.1272182913563835,
      "learning_rate": 9.76006553766365e-07,
      "loss": 1.1418,
      "step": 20
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 3.9017069463911214,
      "learning_rate": 9.465575080933957e-07,
      "loss": 1.0497,
      "step": 25
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 3.555119976875634,
      "learning_rate": 9.063289569141251e-07,
      "loss": 1.0068,
      "step": 30
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 3.650031085041019,
      "learning_rate": 8.562919820737535e-07,
      "loss": 1.0061,
      "step": 35
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 3.595208685101446,
      "learning_rate": 7.97654432138333e-07,
      "loss": 0.945,
      "step": 40
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 3.486796917657139,
      "learning_rate": 7.318317659926636e-07,
      "loss": 0.9177,
      "step": 45
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 3.4158180790128356,
      "learning_rate": 6.604128849076838e-07,
      "loss": 0.8951,
      "step": 50
    },
    {
      "epoch": 1.3513513513513513,
      "eval_loss": 0.957748532295227,
      "eval_runtime": 19.0605,
      "eval_samples_per_second": 55.088,
      "eval_steps_per_second": 0.892,
      "step": 50
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 3.449348101092953,
      "learning_rate": 5.851217778611993e-07,
      "loss": 0.8883,
      "step": 55
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 3.4975815259556406,
      "learning_rate": 5.077759059601755e-07,
      "loss": 0.8608,
      "step": 60
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 3.4676437271759077,
      "learning_rate": 4.302423305280385e-07,
      "loss": 0.864,
      "step": 65
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 3.599315465219125,
      "learning_rate": 3.54392643886374e-07,
      "loss": 0.8678,
      "step": 70
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 3.4514740150902155,
      "learning_rate": 2.8205779076231446e-07,
      "loss": 0.8404,
      "step": 75
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 3.4730369565262955,
      "learning_rate": 2.1498387089310865e-07,
      "loss": 0.8086,
      "step": 80
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 3.512615862231549,
      "learning_rate": 1.5478998971412666e-07,
      "loss": 0.8098,
      "step": 85
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 3.3603433022593414,
      "learning_rate": 1.0292917457762323e-07,
      "loss": 0.8162,
      "step": 90
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 3.5442578486592926,
      "learning_rate": 6.065329995036572e-08,
      "loss": 0.7922,
      "step": 95
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 3.356128248896506,
      "learning_rate": 2.8982868265005454e-08,
      "loss": 0.8199,
      "step": 100
    },
    {
      "epoch": 2.7027027027027026,
      "eval_loss": 0.9323567748069763,
      "eval_runtime": 18.695,
      "eval_samples_per_second": 56.165,
      "eval_steps_per_second": 0.909,
      "step": 100
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 3.4800482691101,
      "learning_rate": 8.682375888868166e-09,
      "loss": 0.7976,
      "step": 105
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 3.5656792050894874,
      "learning_rate": 2.418588540059607e-10,
      "loss": 0.8133,
      "step": 110
    },
    {
      "epoch": 3.0,
      "step": 111,
      "total_flos": 654272366641152.0,
      "train_loss": 0.9774922261366973,
      "train_runtime": 1527.7968,
      "train_samples_per_second": 18.556,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 5,
  "max_steps": 111,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 654272366641152.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}