{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9888412017167383,
  "eval_steps": 500,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13733905579399142,
      "grad_norm": 0.27025100588798523,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.3649,
      "step": 10
    },
    {
      "epoch": 0.27467811158798283,
      "grad_norm": 0.11594237387180328,
      "learning_rate": 4.9812354578598874e-05,
      "loss": 0.2691,
      "step": 20
    },
    {
      "epoch": 0.41201716738197425,
      "grad_norm": 0.10208791494369507,
      "learning_rate": 4.905487021607461e-05,
      "loss": 0.243,
      "step": 30
    },
    {
      "epoch": 0.5493562231759657,
      "grad_norm": 0.09452749043703079,
      "learning_rate": 4.773356008364812e-05,
      "loss": 0.2153,
      "step": 40
    },
    {
      "epoch": 0.6866952789699571,
      "grad_norm": 0.09533349424600601,
      "learning_rate": 4.587939457093295e-05,
      "loss": 0.2063,
      "step": 50
    },
    {
      "epoch": 0.8240343347639485,
      "grad_norm": 0.10009749233722687,
      "learning_rate": 4.353583374602933e-05,
      "loss": 0.1957,
      "step": 60
    },
    {
      "epoch": 0.9613733905579399,
      "grad_norm": 0.16674572229385376,
      "learning_rate": 4.0757808688362954e-05,
      "loss": 0.1897,
      "step": 70
    },
    {
      "epoch": 1.109871244635193,
      "grad_norm": 0.1086713895201683,
      "learning_rate": 3.7610433950740665e-05,
      "loss": 0.1845,
      "step": 80
    },
    {
      "epoch": 1.2472103004291846,
      "grad_norm": 0.0993642583489418,
      "learning_rate": 3.4167481329421206e-05,
      "loss": 0.1439,
      "step": 90
    },
    {
      "epoch": 1.384549356223176,
      "grad_norm": 0.08131585270166397,
      "learning_rate": 3.0509650715736976e-05,
      "loss": 0.1454,
      "step": 100
    },
    {
      "epoch": 1.5218884120171674,
      "grad_norm": 0.08821457624435425,
      "learning_rate": 2.6722678559039272e-05,
      "loss": 0.1357,
      "step": 110
    },
    {
      "epoch": 1.6592274678111587,
      "grad_norm": 0.08488401770591736,
      "learning_rate": 2.2895328276992324e-05,
      "loss": 0.1333,
      "step": 120
    },
    {
      "epoch": 1.7965665236051502,
      "grad_norm": 0.09474518895149231,
      "learning_rate": 1.911730971629566e-05,
      "loss": 0.1277,
      "step": 130
    },
    {
      "epoch": 1.9339055793991418,
      "grad_norm": 0.0876115933060646,
      "learning_rate": 1.5477176429911934e-05,
      "loss": 0.1212,
      "step": 140
    },
    {
      "epoch": 2.082403433476395,
      "grad_norm": 0.083305723965168,
      "learning_rate": 1.2060250056840089e-05,
      "loss": 0.117,
      "step": 150
    },
    {
      "epoch": 2.219742489270386,
      "grad_norm": 0.0787946954369545,
      "learning_rate": 8.946620455212438e-06,
      "loss": 0.0876,
      "step": 160
    },
    {
      "epoch": 2.3570815450643776,
      "grad_norm": 0.08819948136806488,
      "learning_rate": 6.209268463901047e-06,
      "loss": 0.0865,
      "step": 170
    },
    {
      "epoch": 2.494420600858369,
      "grad_norm": 0.0846785455942154,
      "learning_rate": 3.912355293510298e-06,
      "loss": 0.087,
      "step": 180
    },
    {
      "epoch": 2.6317596566523607,
      "grad_norm": 0.07895786315202713,
      "learning_rate": 2.109718641980815e-06,
      "loss": 0.0844,
      "step": 190
    },
    {
      "epoch": 2.769098712446352,
      "grad_norm": 0.07565450668334961,
      "learning_rate": 8.436107845804842e-07,
      "loss": 0.0863,
      "step": 200
    },
    {
      "epoch": 2.9064377682403433,
      "grad_norm": 0.07621210813522339,
      "learning_rate": 1.437082163835035e-07,
      "loss": 0.0849,
      "step": 210
    },
    {
      "epoch": 2.9888412017167383,
      "step": 216,
      "total_flos": 6237706816323584.0,
      "train_loss": 0.15508435997698042,
      "train_runtime": 58329.4214,
      "train_samples_per_second": 1.917,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 10,
  "max_steps": 216,
  "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": 6237706816323584.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}