{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 78.88154602050781,
      "learning_rate": 4.880952380952381e-05,
      "loss": 11.376,
      "step": 1
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 55.407405853271484,
      "learning_rate": 4.761904761904762e-05,
      "loss": 12.4044,
      "step": 2
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 38.84520721435547,
      "learning_rate": 4.642857142857143e-05,
      "loss": 13.4963,
      "step": 3
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 30.360435485839844,
      "learning_rate": 4.523809523809524e-05,
      "loss": 11.8735,
      "step": 4
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 25.831832885742188,
      "learning_rate": 4.404761904761905e-05,
      "loss": 9.3702,
      "step": 5
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 28.620595932006836,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 10.2619,
      "step": 6
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 25.361881256103516,
      "learning_rate": 4.166666666666667e-05,
      "loss": 8.728,
      "step": 7
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 24.713163375854492,
      "learning_rate": 4.047619047619048e-05,
      "loss": 8.1379,
      "step": 8
    },
    {
      "epoch": 0.64,
      "grad_norm": 24.688568115234375,
      "learning_rate": 3.928571428571429e-05,
      "loss": 8.9647,
      "step": 9
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 29.177001953125,
      "learning_rate": 3.809523809523809e-05,
      "loss": 11.1367,
      "step": 10
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 28.675586700439453,
      "learning_rate": 3.690476190476191e-05,
      "loss": 9.4416,
      "step": 11
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 25.128711700439453,
      "learning_rate": 3.571428571428572e-05,
      "loss": 11.7866,
      "step": 12
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 36.48625946044922,
      "learning_rate": 3.4523809523809526e-05,
      "loss": 9.5622,
      "step": 13
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 29.663257598876953,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.2895,
      "step": 14
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.935419082641602,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 0.6347,
      "step": 15
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5814908742904663,
      "eval_runtime": 1.9065,
      "eval_samples_per_second": 52.451,
      "eval_steps_per_second": 13.113,
      "step": 15
    },
    {
      "epoch": 1.0711111111111111,
      "grad_norm": 20.02933120727539,
      "learning_rate": 3.095238095238095e-05,
      "loss": 7.847,
      "step": 16
    },
    {
      "epoch": 1.1422222222222222,
      "grad_norm": 17.20073699951172,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 5.6945,
      "step": 17
    },
    {
      "epoch": 1.2133333333333334,
      "grad_norm": 18.52574920654297,
      "learning_rate": 2.857142857142857e-05,
      "loss": 7.3088,
      "step": 18
    },
    {
      "epoch": 1.2844444444444445,
      "grad_norm": 20.511579513549805,
      "learning_rate": 2.7380952380952383e-05,
      "loss": 7.4839,
      "step": 19
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 21.824100494384766,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 7.7011,
      "step": 20
    },
    {
      "epoch": 1.4266666666666667,
      "grad_norm": 18.337739944458008,
      "learning_rate": 2.5e-05,
      "loss": 8.2713,
      "step": 21
    },
    {
      "epoch": 1.4977777777777779,
      "grad_norm": 22.034822463989258,
      "learning_rate": 2.380952380952381e-05,
      "loss": 7.8916,
      "step": 22
    },
    {
      "epoch": 1.568888888888889,
      "grad_norm": 30.39559555053711,
      "learning_rate": 2.261904761904762e-05,
      "loss": 8.2024,
      "step": 23
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 22.20236587524414,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 8.1544,
      "step": 24
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 23.32938003540039,
      "learning_rate": 2.023809523809524e-05,
      "loss": 6.5783,
      "step": 25
    },
    {
      "epoch": 1.7822222222222224,
      "grad_norm": 21.323816299438477,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 9.7118,
      "step": 26
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 22.239408493041992,
      "learning_rate": 1.785714285714286e-05,
      "loss": 8.6708,
      "step": 27
    },
    {
      "epoch": 1.9244444444444444,
      "grad_norm": 23.096269607543945,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 8.6035,
      "step": 28
    },
    {
      "epoch": 1.9955555555555555,
      "grad_norm": 21.888853073120117,
      "learning_rate": 1.5476190476190476e-05,
      "loss": 7.8134,
      "step": 29
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.1928675174713135,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.3335,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5763611793518066,
      "eval_runtime": 1.9106,
      "eval_samples_per_second": 52.339,
      "eval_steps_per_second": 13.085,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1790912424280064e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}