{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017191361340926185,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003438272268185237,
      "grad_norm": 11.813494682312012,
      "learning_rate": 1e-05,
      "loss": 5.0582,
      "step": 1
    },
    {
      "epoch": 0.0003438272268185237,
      "eval_loss": 6.089541435241699,
      "eval_runtime": 181.7702,
      "eval_samples_per_second": 26.952,
      "eval_steps_per_second": 13.479,
      "step": 1
    },
    {
      "epoch": 0.0006876544536370474,
      "grad_norm": 11.068693161010742,
      "learning_rate": 2e-05,
      "loss": 4.7544,
      "step": 2
    },
    {
      "epoch": 0.0006876544536370474,
      "eval_loss": 5.879291534423828,
      "eval_runtime": 68.2341,
      "eval_samples_per_second": 71.797,
      "eval_steps_per_second": 35.906,
      "step": 2
    },
    {
      "epoch": 0.0010314816804555711,
      "grad_norm": 15.039040565490723,
      "learning_rate": 3e-05,
      "loss": 6.1838,
      "step": 3
    },
    {
      "epoch": 0.0013753089072740948,
      "grad_norm": 10.66008186340332,
      "learning_rate": 4e-05,
      "loss": 4.5854,
      "step": 4
    },
    {
      "epoch": 0.0013753089072740948,
      "eval_loss": 5.231777191162109,
      "eval_runtime": 111.1543,
      "eval_samples_per_second": 44.074,
      "eval_steps_per_second": 22.041,
      "step": 4
    },
    {
      "epoch": 0.0017191361340926185,
      "grad_norm": 13.945072174072266,
      "learning_rate": 5e-05,
      "loss": 5.3924,
      "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": 991192531599360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}