{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 13.665339392120242,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.7972,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1326594871506976,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.5693,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.229628721329319,
      "learning_rate": 9.992203820909906e-06,
      "loss": 0.4321,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 23.98083749455022,
      "learning_rate": 9.904775776745959e-06,
      "loss": 0.3428,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4779282929051816,
      "learning_rate": 9.721881851187406e-06,
      "loss": 0.297,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.7030928394182192,
      "learning_rate": 9.44708186645649e-06,
      "loss": 0.2048,
      "step": 60
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.36208494729096075,
      "learning_rate": 9.085724491675642e-06,
      "loss": 0.1956,
      "step": 70
    },
    {
      "epoch": 3.2,
      "grad_norm": 15.852415619527582,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.1364,
      "step": 80
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.4440039793906722,
      "learning_rate": 8.133019056822303e-06,
      "loss": 0.1061,
      "step": 90
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.42486560707680776,
      "learning_rate": 7.560214324352858e-06,
      "loss": 0.0929,
      "step": 100
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.44641303384271735,
      "learning_rate": 6.9375779322605154e-06,
      "loss": 0.0502,
      "step": 110
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.24553081143144395,
      "learning_rate": 6.277228789678953e-06,
      "loss": 0.0508,
      "step": 120
    },
    {
      "epoch": 5.2,
      "grad_norm": 0.21311247261529426,
      "learning_rate": 5.592019841532507e-06,
      "loss": 0.0367,
      "step": 130
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.2652581124769846,
      "learning_rate": 4.895287900583216e-06,
      "loss": 0.027,
      "step": 140
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.22255970725351767,
      "learning_rate": 4.200594061540827e-06,
      "loss": 0.0246,
      "step": 150
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.20260633596438954,
      "learning_rate": 3.521459749779769e-06,
      "loss": 0.0139,
      "step": 160
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.225354022287482,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.0122,
      "step": 170
    },
    {
      "epoch": 7.2,
      "grad_norm": 44.88434252382171,
      "learning_rate": 2.2621838825372496e-06,
      "loss": 0.0091,
      "step": 180
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.15078014988540728,
      "learning_rate": 1.7065526994065973e-06,
      "loss": 0.0069,
      "step": 190
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.11684871135125384,
      "learning_rate": 1.2150247217412186e-06,
      "loss": 0.0064,
      "step": 200
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.10691723109581759,
      "learning_rate": 7.971669825215789e-07,
      "loss": 0.0045,
      "step": 210
    },
    {
      "epoch": 8.8,
      "grad_norm": 0.0895459643872266,
      "learning_rate": 4.6111260733545714e-07,
      "loss": 0.0043,
      "step": 220
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.10141341473243017,
      "learning_rate": 2.134025123396638e-07,
      "loss": 0.0043,
      "step": 230
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.08426717702147542,
      "learning_rate": 5.8858092767236084e-08,
      "loss": 0.0037,
      "step": 240
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.07136839003077843,
      "learning_rate": 4.87379953478806e-10,
      "loss": 0.0038,
      "step": 250
    },
    {
      "epoch": 10.0,
      "step": 250,
      "total_flos": 502552426708992.0,
      "train_loss": 0.13730106168985368,
      "train_runtime": 20764.2529,
      "train_samples_per_second": 0.384,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 502552426708992.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}