{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.42105263157894735,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 2.732322931289673,
      "learning_rate": 1e-05,
      "loss": 3.895,
      "step": 1
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 3.9015960693359375,
      "eval_runtime": 68.5209,
      "eval_samples_per_second": 0.584,
      "eval_steps_per_second": 0.292,
      "step": 1
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 2.7262046337127686,
      "learning_rate": 2e-05,
      "loss": 3.9939,
      "step": 2
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 2.537787675857544,
      "learning_rate": 3e-05,
      "loss": 3.8642,
      "step": 3
    },
    {
      "epoch": 0.12631578947368421,
      "eval_loss": 3.838761806488037,
      "eval_runtime": 1.1737,
      "eval_samples_per_second": 34.081,
      "eval_steps_per_second": 17.041,
      "step": 3
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 2.600435733795166,
      "learning_rate": 4e-05,
      "loss": 3.5846,
      "step": 4
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.9709930419921875,
      "learning_rate": 5e-05,
      "loss": 3.9756,
      "step": 5
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 2.7780497074127197,
      "learning_rate": 6e-05,
      "loss": 3.5488,
      "step": 6
    },
    {
      "epoch": 0.25263157894736843,
      "eval_loss": 3.5095763206481934,
      "eval_runtime": 1.1753,
      "eval_samples_per_second": 34.033,
      "eval_steps_per_second": 17.016,
      "step": 6
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 3.0028023719787598,
      "learning_rate": 7e-05,
      "loss": 3.2356,
      "step": 7
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 2.84335994720459,
      "learning_rate": 8e-05,
      "loss": 3.409,
      "step": 8
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 2.7537617683410645,
      "learning_rate": 9e-05,
      "loss": 3.1112,
      "step": 9
    },
    {
      "epoch": 0.37894736842105264,
      "eval_loss": 2.9162354469299316,
      "eval_runtime": 1.1763,
      "eval_samples_per_second": 34.004,
      "eval_steps_per_second": 17.002,
      "step": 9
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 2.582125425338745,
      "learning_rate": 0.0001,
      "loss": 3.1332,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8209574469304320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}