{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020559633216143423,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.4365,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001968583161128631,
      "loss": 1.9051,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019297764858882514,
      "loss": 1.7675,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.5579,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.5811,
      "step": 50
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017289686274214118,
      "loss": 1.5127,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000163742398974869,
      "loss": 1.5401,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015358267949789966,
      "loss": 1.4744,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014257792915650728,
      "loss": 1.529,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4882,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011873813145857249,
      "loss": 1.4626,
      "step": 110
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010627905195293135,
      "loss": 1.5641,
      "step": 120
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.5117,
      "step": 130
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.126186854142752e-05,
      "loss": 1.5066,
      "step": 140
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.5195,
      "step": 150
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.4811,
      "step": 160
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 1.433,
      "step": 170
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 1.5147,
      "step": 180
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.5148,
      "step": 190
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.4972,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 1.4183,
      "step": 210
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.4444,
      "step": 220
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 1.4812,
      "step": 230
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.885298685522235e-07,
      "loss": 1.4718,
      "step": 240
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 1.5381,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 5155815837155328.0,
  "trial_name": null,
  "trial_params": null
}