{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001870251315020456,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003740502630040912,
      "grad_norm": 41.647518157958984,
      "learning_rate": 1e-05,
      "loss": 72.8249,
      "step": 1
    },
    {
      "epoch": 0.0003740502630040912,
      "eval_loss": 4.466118335723877,
      "eval_runtime": 538.6833,
      "eval_samples_per_second": 8.359,
      "eval_steps_per_second": 4.181,
      "step": 1
    },
    {
      "epoch": 0.0007481005260081823,
      "grad_norm": 38.24934005737305,
      "learning_rate": 2e-05,
      "loss": 70.9894,
      "step": 2
    },
    {
      "epoch": 0.0007481005260081823,
      "eval_loss": 4.410397529602051,
      "eval_runtime": 368.6515,
      "eval_samples_per_second": 12.215,
      "eval_steps_per_second": 6.109,
      "step": 2
    },
    {
      "epoch": 0.0011221507890122736,
      "grad_norm": 43.835487365722656,
      "learning_rate": 3e-05,
      "loss": 74.882,
      "step": 3
    },
    {
      "epoch": 0.0014962010520163647,
      "grad_norm": 38.10905075073242,
      "learning_rate": 4e-05,
      "loss": 72.5016,
      "step": 4
    },
    {
      "epoch": 0.0014962010520163647,
      "eval_loss": 4.347618103027344,
      "eval_runtime": 248.1822,
      "eval_samples_per_second": 18.144,
      "eval_steps_per_second": 9.074,
      "step": 4
    },
    {
      "epoch": 0.001870251315020456,
      "grad_norm": 41.459442138671875,
      "learning_rate": 5e-05,
      "loss": 70.2847,
      "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": 3257466271825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}