{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5405405405405406,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 43.9290657043457,
      "learning_rate": 1.9856576576576577e-05,
      "loss": 0.6499,
      "step": 200
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 13.308595657348633,
      "learning_rate": 1.9712432432432433e-05,
      "loss": 0.568,
      "step": 400
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 5.098663806915283,
      "learning_rate": 1.956828828828829e-05,
      "loss": 0.5371,
      "step": 600
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 9.126262664794922,
      "learning_rate": 1.9424144144144147e-05,
      "loss": 0.5181,
      "step": 800
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 15.761275291442871,
      "learning_rate": 1.9280000000000002e-05,
      "loss": 0.504,
      "step": 1000
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": 33.255863189697266,
      "learning_rate": 1.9135855855855857e-05,
      "loss": 0.5017,
      "step": 1200
    },
    {
      "epoch": 0.15135135135135136,
      "grad_norm": 6.04021692276001,
      "learning_rate": 1.8991711711711712e-05,
      "loss": 0.468,
      "step": 1400
    },
    {
      "epoch": 0.17297297297297298,
      "grad_norm": 15.048690795898438,
      "learning_rate": 1.8847567567567568e-05,
      "loss": 0.5056,
      "step": 1600
    },
    {
      "epoch": 0.1945945945945946,
      "grad_norm": 22.5860538482666,
      "learning_rate": 1.8703423423423426e-05,
      "loss": 0.4601,
      "step": 1800
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 12.32684326171875,
      "learning_rate": 1.855927927927928e-05,
      "loss": 0.4401,
      "step": 2000
    },
    {
      "epoch": 0.23783783783783785,
      "grad_norm": 9.132744789123535,
      "learning_rate": 1.8415135135135137e-05,
      "loss": 0.4707,
      "step": 2200
    },
    {
      "epoch": 0.2594594594594595,
      "grad_norm": 10.921464920043945,
      "learning_rate": 1.8270990990990992e-05,
      "loss": 0.4676,
      "step": 2400
    },
    {
      "epoch": 0.2810810810810811,
      "grad_norm": 20.87602424621582,
      "learning_rate": 1.8126846846846847e-05,
      "loss": 0.469,
      "step": 2600
    },
    {
      "epoch": 0.3027027027027027,
      "grad_norm": 27.636375427246094,
      "learning_rate": 1.7982702702702702e-05,
      "loss": 0.4419,
      "step": 2800
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 8.047364234924316,
      "learning_rate": 1.783855855855856e-05,
      "loss": 0.4331,
      "step": 3000
    },
    {
      "epoch": 0.34594594594594597,
      "grad_norm": 14.144438743591309,
      "learning_rate": 1.7694414414414416e-05,
      "loss": 0.4444,
      "step": 3200
    },
    {
      "epoch": 0.3675675675675676,
      "grad_norm": 13.833978652954102,
      "learning_rate": 1.755027027027027e-05,
      "loss": 0.4269,
      "step": 3400
    },
    {
      "epoch": 0.3891891891891892,
      "grad_norm": 7.048819541931152,
      "learning_rate": 1.7406126126126127e-05,
      "loss": 0.4518,
      "step": 3600
    },
    {
      "epoch": 0.41081081081081083,
      "grad_norm": 16.350954055786133,
      "learning_rate": 1.7261981981981982e-05,
      "loss": 0.4306,
      "step": 3800
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 36.817256927490234,
      "learning_rate": 1.7117837837837837e-05,
      "loss": 0.3993,
      "step": 4000
    },
    {
      "epoch": 0.4540540540540541,
      "grad_norm": 6.8075151443481445,
      "learning_rate": 1.6973693693693696e-05,
      "loss": 0.4624,
      "step": 4200
    },
    {
      "epoch": 0.4756756756756757,
      "grad_norm": 22.440227508544922,
      "learning_rate": 1.682954954954955e-05,
      "loss": 0.4062,
      "step": 4400
    },
    {
      "epoch": 0.4972972972972973,
      "grad_norm": 27.693946838378906,
      "learning_rate": 1.6685405405405406e-05,
      "loss": 0.3986,
      "step": 4600
    },
    {
      "epoch": 0.518918918918919,
      "grad_norm": 5.609838485717773,
      "learning_rate": 1.6541261261261262e-05,
      "loss": 0.418,
      "step": 4800
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 9.340408325195312,
      "learning_rate": 1.6397117117117117e-05,
      "loss": 0.4292,
      "step": 5000
    }
  ],
  "logging_steps": 200,
  "max_steps": 27750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.115253374976e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}