{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.5,
  "global_step": 13000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 1.95e-05,
      "loss": 2.5291,
      "step": 500
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9e-05,
      "loss": 2.5099,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 2.4884,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.8e-05,
      "loss": 2.487,
      "step": 2000
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 2.4754,
      "step": 2500
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.7e-05,
      "loss": 2.465,
      "step": 3000
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.65e-05,
      "loss": 2.4567,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.4565,
      "step": 4000
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.55e-05,
      "loss": 2.4296,
      "step": 4500
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.4324,
      "step": 5000
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.45e-05,
      "loss": 2.4161,
      "step": 5500
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.4e-05,
      "loss": 2.4061,
      "step": 6000
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.4308149814605713,
      "eval_runtime": 90.0551,
      "eval_samples_per_second": 177.669,
      "eval_steps_per_second": 11.104,
      "step": 6000
    },
    {
      "epoch": 3.25,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 2.349,
      "step": 6500
    },
    {
      "epoch": 3.5,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 2.3544,
      "step": 7000
    },
    {
      "epoch": 3.75,
      "learning_rate": 1.25e-05,
      "loss": 2.3463,
      "step": 7500
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.2e-05,
      "loss": 2.3461,
      "step": 8000
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.4396936893463135,
      "eval_runtime": 90.0717,
      "eval_samples_per_second": 177.636,
      "eval_steps_per_second": 11.102,
      "step": 8000
    },
    {
      "epoch": 4.25,
      "learning_rate": 1.15e-05,
      "loss": 2.2347,
      "step": 8500
    },
    {
      "epoch": 4.5,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 2.2444,
      "step": 9000
    },
    {
      "epoch": 4.75,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 2.2319,
      "step": 9500
    },
    {
      "epoch": 5.0,
      "learning_rate": 1e-05,
      "loss": 2.2281,
      "step": 10000
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.4722118377685547,
      "eval_runtime": 90.0452,
      "eval_samples_per_second": 177.689,
      "eval_steps_per_second": 11.106,
      "step": 10000
    },
    {
      "epoch": 5.25,
      "learning_rate": 9.5e-06,
      "loss": 2.0556,
      "step": 10500
    },
    {
      "epoch": 5.5,
      "learning_rate": 9e-06,
      "loss": 2.0456,
      "step": 11000
    },
    {
      "epoch": 5.75,
      "learning_rate": 8.5e-06,
      "loss": 2.0644,
      "step": 11500
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0578,
      "step": 12000
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.577911376953125,
      "eval_runtime": 90.5865,
      "eval_samples_per_second": 176.627,
      "eval_steps_per_second": 11.039,
      "step": 12000
    },
    {
      "epoch": 6.25,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.804,
      "step": 12500
    },
    {
      "epoch": 6.5,
      "learning_rate": 7e-06,
      "loss": 1.8018,
      "step": 13000
    }
  ],
  "max_steps": 20000,
  "num_train_epochs": 10,
  "total_flos": 6495300778518528.0,
  "trial_name": null,
  "trial_params": null
}