{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 279,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03590664272890485,
      "grad_norm": 4.158227443695068,
      "learning_rate": 5.142857142857143e-06,
      "loss": 1.4155162811279296,
      "step": 10
    },
    {
      "epoch": 0.0718132854578097,
      "grad_norm": 1.651964545249939,
      "learning_rate": 7.992974927057286e-06,
      "loss": 0.805302906036377,
      "step": 20
    },
    {
      "epoch": 0.10771992818671454,
      "grad_norm": 1.1457046270370483,
      "learning_rate": 7.936922311790387e-06,
      "loss": 0.6863783836364746,
      "step": 30
    },
    {
      "epoch": 0.1436265709156194,
      "grad_norm": 1.0957046747207642,
      "learning_rate": 7.825603937106089e-06,
      "loss": 0.6478697299957276,
      "step": 40
    },
    {
      "epoch": 0.17953321364452424,
      "grad_norm": 1.0592354536056519,
      "learning_rate": 7.660582468972073e-06,
      "loss": 0.630420446395874,
      "step": 50
    },
    {
      "epoch": 0.21543985637342908,
      "grad_norm": 1.193621277809143,
      "learning_rate": 7.444174447069421e-06,
      "loss": 0.6120198726654053,
      "step": 60
    },
    {
      "epoch": 0.2513464991023339,
      "grad_norm": 1.2658783197402954,
      "learning_rate": 7.179417765653413e-06,
      "loss": 0.6067015647888183,
      "step": 70
    },
    {
      "epoch": 0.2872531418312388,
      "grad_norm": 1.2949614524841309,
      "learning_rate": 6.870029028177324e-06,
      "loss": 0.5879001617431641,
      "step": 80
    },
    {
      "epoch": 0.3231597845601436,
      "grad_norm": 1.060629963874817,
      "learning_rate": 6.520351374326845e-06,
      "loss": 0.5899921417236328,
      "step": 90
    },
    {
      "epoch": 0.3590664272890485,
      "grad_norm": 1.0478813648223877,
      "learning_rate": 6.1352935118591635e-06,
      "loss": 0.5808853149414063,
      "step": 100
    },
    {
      "epoch": 0.39497307001795334,
      "grad_norm": 1.261673092842102,
      "learning_rate": 5.720260809106082e-06,
      "loss": 0.5790524482727051,
      "step": 110
    },
    {
      "epoch": 0.43087971274685816,
      "grad_norm": 0.9995132088661194,
      "learning_rate": 5.28107941545135e-06,
      "loss": 0.5731555938720703,
      "step": 120
    },
    {
      "epoch": 0.466786355475763,
      "grad_norm": 1.0616153478622437,
      "learning_rate": 4.823914474964393e-06,
      "loss": 0.5686985969543457,
      "step": 130
    },
    {
      "epoch": 0.5026929982046678,
      "grad_norm": 1.0009936094284058,
      "learning_rate": 4.355183581291739e-06,
      "loss": 0.5693955898284913,
      "step": 140
    },
    {
      "epoch": 0.5385996409335727,
      "grad_norm": 0.9809271097183228,
      "learning_rate": 3.8814666887097606e-06,
      "loss": 0.5598339080810547,
      "step": 150
    },
    {
      "epoch": 0.5745062836624776,
      "grad_norm": 0.9185540080070496,
      "learning_rate": 3.4094137439900755e-06,
      "loss": 0.5563373565673828,
      "step": 160
    },
    {
      "epoch": 0.6104129263913824,
      "grad_norm": 0.9326531887054443,
      "learning_rate": 2.94565133572373e-06,
      "loss": 0.5573836326599121,
      "step": 170
    },
    {
      "epoch": 0.6463195691202872,
      "grad_norm": 0.9872980117797852,
      "learning_rate": 2.496689671543048e-06,
      "loss": 0.5560619354248046,
      "step": 180
    },
    {
      "epoch": 0.6822262118491921,
      "grad_norm": 0.8914107084274292,
      "learning_rate": 2.068831189077021e-06,
      "loss": 0.5496598720550537,
      "step": 190
    },
    {
      "epoch": 0.718132854578097,
      "grad_norm": 0.9620088338851929,
      "learning_rate": 1.6680820835421124e-06,
      "loss": 0.5505017757415771,
      "step": 200
    },
    {
      "epoch": 0.7540394973070018,
      "grad_norm": 0.8976511359214783,
      "learning_rate": 1.3000679939271586e-06,
      "loss": 0.5497483253479004,
      "step": 210
    },
    {
      "epoch": 0.7899461400359067,
      "grad_norm": 0.8932470679283142,
      "learning_rate": 9.699550313535194e-07,
      "loss": 0.5485612392425537,
      "step": 220
    },
    {
      "epoch": 0.8258527827648114,
      "grad_norm": 0.9887930154800415,
      "learning_rate": 6.823772581991929e-07,
      "loss": 0.5506965160369873,
      "step": 230
    },
    {
      "epoch": 0.8617594254937163,
      "grad_norm": 0.9191465973854065,
      "learning_rate": 4.413716360210111e-07,
      "loss": 0.5589346885681152,
      "step": 240
    },
    {
      "epoch": 0.8976660682226212,
      "grad_norm": 0.8461963534355164,
      "learning_rate": 2.503213554635164e-07,
      "loss": 0.5451088905334472,
      "step": 250
    },
    {
      "epoch": 0.933572710951526,
      "grad_norm": 0.8567756414413452,
      "learning_rate": 1.11908343678357e-07,
      "loss": 0.5363705635070801,
      "step": 260
    },
    {
      "epoch": 0.9694793536804309,
      "grad_norm": 0.8579103946685791,
      "learning_rate": 2.8075615945932328e-08,
      "loss": 0.5481849670410156,
      "step": 270
    },
    {
      "epoch": 1.0,
      "step": 279,
      "total_flos": 1.3482902468228547e+18,
      "train_loss": 0.6133034630915597,
      "train_runtime": 1004.8538,
      "train_samples_per_second": 35.45,
      "train_steps_per_second": 0.278
    }
  ],
  "logging_steps": 10,
  "max_steps": 279,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3482902468228547e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}