{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0389610389610389,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05772005772005772,
      "grad_norm": 0.036376953125,
      "learning_rate": 0.0001,
      "loss": 0.7562,
      "step": 5
    },
    {
      "epoch": 0.11544011544011544,
      "grad_norm": 0.0206298828125,
      "learning_rate": 0.0001,
      "loss": 0.5993,
      "step": 10
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 0.0244140625,
      "learning_rate": 0.0001,
      "loss": 0.5209,
      "step": 15
    },
    {
      "epoch": 0.23088023088023088,
      "grad_norm": 0.0673828125,
      "learning_rate": 0.0001,
      "loss": 0.5029,
      "step": 20
    },
    {
      "epoch": 0.2886002886002886,
      "grad_norm": 0.04150390625,
      "learning_rate": 0.0001,
      "loss": 0.622,
      "step": 25
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 0.0284423828125,
      "learning_rate": 0.0001,
      "loss": 0.5561,
      "step": 30
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.0189208984375,
      "learning_rate": 0.0001,
      "loss": 0.4707,
      "step": 35
    },
    {
      "epoch": 0.46176046176046176,
      "grad_norm": 0.019775390625,
      "learning_rate": 0.0001,
      "loss": 0.4331,
      "step": 40
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.0233154296875,
      "learning_rate": 0.0001,
      "loss": 0.534,
      "step": 45
    },
    {
      "epoch": 0.5772005772005772,
      "grad_norm": 0.0185546875,
      "learning_rate": 0.0001,
      "loss": 0.5314,
      "step": 50
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.0169677734375,
      "learning_rate": 0.0001,
      "loss": 0.4802,
      "step": 55
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 0.0172119140625,
      "learning_rate": 0.0001,
      "loss": 0.4332,
      "step": 60
    },
    {
      "epoch": 0.7503607503607503,
      "grad_norm": 0.021728515625,
      "learning_rate": 0.0001,
      "loss": 0.4812,
      "step": 65
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.0155029296875,
      "learning_rate": 0.0001,
      "loss": 0.5443,
      "step": 70
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 0.0159912109375,
      "learning_rate": 0.0001,
      "loss": 0.4805,
      "step": 75
    },
    {
      "epoch": 0.9235209235209235,
      "grad_norm": 0.0146484375,
      "learning_rate": 0.0001,
      "loss": 0.4377,
      "step": 80
    },
    {
      "epoch": 0.9812409812409812,
      "grad_norm": 0.019775390625,
      "learning_rate": 0.0001,
      "loss": 0.4548,
      "step": 85
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 0.018310546875,
      "learning_rate": 0.0001,
      "loss": 0.5309,
      "step": 90
    }
  ],
  "logging_steps": 5,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.286644455131546e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}