{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07398843930635839,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018497109826589597,
      "grad_norm": 484.24322509765625,
      "learning_rate": 1e-05,
      "loss": 146.304,
      "step": 1
    },
    {
      "epoch": 0.018497109826589597,
      "eval_loss": 8.745285987854004,
      "eval_runtime": 15.3357,
      "eval_samples_per_second": 5.999,
      "eval_steps_per_second": 3.0,
      "step": 1
    },
    {
      "epoch": 0.03699421965317919,
      "grad_norm": 564.8761596679688,
      "learning_rate": 2e-05,
      "loss": 142.457,
      "step": 2
    },
    {
      "epoch": 0.03699421965317919,
      "eval_loss": 8.309063911437988,
      "eval_runtime": 2.3663,
      "eval_samples_per_second": 38.879,
      "eval_steps_per_second": 19.439,
      "step": 2
    },
    {
      "epoch": 0.055491329479768786,
      "grad_norm": 552.8171997070312,
      "learning_rate": 3e-05,
      "loss": 140.1018,
      "step": 3
    },
    {
      "epoch": 0.07398843930635839,
      "grad_norm": 489.36383056640625,
      "learning_rate": 4e-05,
      "loss": 137.1624,
      "step": 4
    },
    {
      "epoch": 0.07398843930635839,
      "eval_loss": 6.819180488586426,
      "eval_runtime": 2.3703,
      "eval_samples_per_second": 38.814,
      "eval_steps_per_second": 19.407,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3330072593301504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}