{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3577017661524704,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017885088307623517,
      "grad_norm": 0.27167433500289917,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 1.9206,
      "step": 10
    },
    {
      "epoch": 0.035770176615247035,
      "grad_norm": 0.2490677386522293,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 1.8864,
      "step": 20
    },
    {
      "epoch": 0.05365526492287056,
      "grad_norm": 0.23479315638542175,
      "learning_rate": 1.785714285714286e-05,
      "loss": 1.8092,
      "step": 30
    },
    {
      "epoch": 0.07154035323049407,
      "grad_norm": 0.2516893446445465,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.6878,
      "step": 40
    },
    {
      "epoch": 0.0894254415381176,
      "grad_norm": 0.30081456899642944,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 1.4673,
      "step": 50
    },
    {
      "epoch": 0.0894254415381176,
      "eval_loss": 1.3079078197479248,
      "eval_runtime": 340.2145,
      "eval_samples_per_second": 5.843,
      "eval_steps_per_second": 2.922,
      "step": 50
    },
    {
      "epoch": 0.10731052984574112,
      "grad_norm": 0.40885159373283386,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.1216,
      "step": 60
    },
    {
      "epoch": 0.12519561815336464,
      "grad_norm": 0.34105631709098816,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.623,
      "step": 70
    },
    {
      "epoch": 0.14308070646098814,
      "grad_norm": 0.08575189858675003,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.321,
      "step": 80
    },
    {
      "epoch": 0.16096579476861167,
      "grad_norm": 0.06351594626903534,
      "learning_rate": 5.3571428571428575e-05,
      "loss": 0.2671,
      "step": 90
    },
    {
      "epoch": 0.1788508830762352,
      "grad_norm": 0.044943634420633316,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 0.2634,
      "step": 100
    },
    {
      "epoch": 0.1788508830762352,
      "eval_loss": 0.2529277801513672,
      "eval_runtime": 340.0791,
      "eval_samples_per_second": 5.846,
      "eval_steps_per_second": 2.923,
      "step": 100
    },
    {
      "epoch": 0.1967359713838587,
      "grad_norm": 0.04525942727923393,
      "learning_rate": 6.547619047619048e-05,
      "loss": 0.2476,
      "step": 110
    },
    {
      "epoch": 0.21462105969148224,
      "grad_norm": 0.03497561439871788,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.2364,
      "step": 120
    },
    {
      "epoch": 0.23250614799910574,
      "grad_norm": 0.03806141018867493,
      "learning_rate": 7.738095238095239e-05,
      "loss": 0.2375,
      "step": 130
    },
    {
      "epoch": 0.25039123630672927,
      "grad_norm": 0.03912373259663582,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.2458,
      "step": 140
    },
    {
      "epoch": 0.2682763246143528,
      "grad_norm": 0.038528475910425186,
      "learning_rate": 8.92857142857143e-05,
      "loss": 0.2356,
      "step": 150
    },
    {
      "epoch": 0.2682763246143528,
      "eval_loss": 0.2338634878396988,
      "eval_runtime": 340.1092,
      "eval_samples_per_second": 5.845,
      "eval_steps_per_second": 2.923,
      "step": 150
    },
    {
      "epoch": 0.2861614129219763,
      "grad_norm": 0.033717814832925797,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.2328,
      "step": 160
    },
    {
      "epoch": 0.3040465012295998,
      "grad_norm": 0.034611135721206665,
      "learning_rate": 9.98674618952949e-05,
      "loss": 0.232,
      "step": 170
    },
    {
      "epoch": 0.32193158953722334,
      "grad_norm": 0.03772770240902901,
      "learning_rate": 9.920477137176939e-05,
      "loss": 0.2321,
      "step": 180
    },
    {
      "epoch": 0.33981667784484687,
      "grad_norm": 0.03764208406209946,
      "learning_rate": 9.854208084824388e-05,
      "loss": 0.2252,
      "step": 190
    },
    {
      "epoch": 0.3577017661524704,
      "grad_norm": 0.04233132675290108,
      "learning_rate": 9.787939032471835e-05,
      "loss": 0.2255,
      "step": 200
    },
    {
      "epoch": 0.3577017661524704,
      "eval_loss": 0.22211842238903046,
      "eval_runtime": 340.2159,
      "eval_samples_per_second": 5.843,
      "eval_steps_per_second": 2.922,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1677,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.028581969459413e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}