{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10075566750629723,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00559753708368318,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001,
      "loss": 4.5193,
      "step": 5
    },
    {
      "epoch": 0.01119507416736636,
      "grad_norm": 0.68359375,
      "learning_rate": 0.0001,
      "loss": 2.8387,
      "step": 10
    },
    {
      "epoch": 0.016792611251049538,
      "grad_norm": 0.484375,
      "learning_rate": 0.0001,
      "loss": 2.1966,
      "step": 15
    },
    {
      "epoch": 0.02239014833473272,
      "grad_norm": 0.51953125,
      "learning_rate": 0.0001,
      "loss": 2.0024,
      "step": 20
    },
    {
      "epoch": 0.027987685418415897,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 1.7735,
      "step": 25
    },
    {
      "epoch": 0.033585222502099076,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001,
      "loss": 1.6781,
      "step": 30
    },
    {
      "epoch": 0.039182759585782254,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0001,
      "loss": 1.6619,
      "step": 35
    },
    {
      "epoch": 0.04478029666946544,
      "grad_norm": 0.3125,
      "learning_rate": 0.0001,
      "loss": 1.6361,
      "step": 40
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0001,
      "loss": 1.6153,
      "step": 45
    },
    {
      "epoch": 0.055975370836831795,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0001,
      "loss": 1.5201,
      "step": 50
    },
    {
      "epoch": 0.06157290792051497,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 1.5211,
      "step": 55
    },
    {
      "epoch": 0.06717044500419815,
      "grad_norm": 0.2392578125,
      "learning_rate": 0.0001,
      "loss": 1.5359,
      "step": 60
    },
    {
      "epoch": 0.07276798208788134,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001,
      "loss": 1.5686,
      "step": 65
    },
    {
      "epoch": 0.07836551917156451,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001,
      "loss": 1.5732,
      "step": 70
    },
    {
      "epoch": 0.08396305625524769,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0001,
      "loss": 1.5958,
      "step": 75
    },
    {
      "epoch": 0.08956059333893088,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0001,
      "loss": 1.5006,
      "step": 80
    },
    {
      "epoch": 0.09515813042261405,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0001,
      "loss": 1.5051,
      "step": 85
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.314453125,
      "learning_rate": 0.0001,
      "loss": 1.5649,
      "step": 90
    }
  ],
  "logging_steps": 5,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 9.171731697967104e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}