{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07428040854224698,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014856081708449397,
      "grad_norm": 1.7075327634811401,
      "learning_rate": 1e-05,
      "loss": 39.2083,
      "step": 1
    },
    {
      "epoch": 0.014856081708449397,
      "eval_loss": 2.365845203399658,
      "eval_runtime": 53.105,
      "eval_samples_per_second": 2.147,
      "eval_steps_per_second": 1.073,
      "step": 1
    },
    {
      "epoch": 0.029712163416898793,
      "grad_norm": 1.8963137865066528,
      "learning_rate": 2e-05,
      "loss": 38.9072,
      "step": 2
    },
    {
      "epoch": 0.029712163416898793,
      "eval_loss": 2.3638737201690674,
      "eval_runtime": 27.4723,
      "eval_samples_per_second": 4.15,
      "eval_steps_per_second": 2.075,
      "step": 2
    },
    {
      "epoch": 0.04456824512534819,
      "grad_norm": 1.9398624897003174,
      "learning_rate": 3e-05,
      "loss": 37.8162,
      "step": 3
    },
    {
      "epoch": 0.059424326833797586,
      "grad_norm": 2.3769500255584717,
      "learning_rate": 4e-05,
      "loss": 38.1807,
      "step": 4
    },
    {
      "epoch": 0.059424326833797586,
      "eval_loss": 2.3615305423736572,
      "eval_runtime": 27.4708,
      "eval_samples_per_second": 4.15,
      "eval_steps_per_second": 2.075,
      "step": 4
    },
    {
      "epoch": 0.07428040854224698,
      "grad_norm": 1.8784000873565674,
      "learning_rate": 5e-05,
      "loss": 37.277,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.258566158647296e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}