{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 7.939234477653451,
      "learning_rate": 5e-07,
      "loss": 1.4592,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.674129849441835,
      "learning_rate": 8.742553740855505e-07,
      "loss": 1.4295,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4871999025344849,
      "eval_runtime": 4.0086,
      "eval_samples_per_second": 11.226,
      "eval_steps_per_second": 0.748,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.446393481808942,
      "learning_rate": 3.2269755647873214e-07,
      "loss": 1.3958,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4525436162948608,
      "eval_runtime": 4.1386,
      "eval_samples_per_second": 10.873,
      "eval_steps_per_second": 0.725,
      "step": 10
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.1815285521818035,
      "learning_rate": 0.0,
      "loss": 1.3727,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.4498653411865234,
      "eval_runtime": 4.1282,
      "eval_samples_per_second": 10.901,
      "eval_steps_per_second": 0.727,
      "step": 15
    },
    {
      "epoch": 3.0,
      "step": 15,
      "total_flos": 3088349921280.0,
      "train_loss": 1.401317008336385,
      "train_runtime": 256.842,
      "train_samples_per_second": 3.668,
      "train_steps_per_second": 0.058
    }
  ],
  "logging_steps": 5,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3088349921280.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}