{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5925925925925926,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 16.014848709106445,
      "learning_rate": 9e-06,
      "loss": 8.78155746459961,
      "step": 10
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 8.823369026184082,
      "learning_rate": 1.9e-05,
      "loss": 6.965694427490234,
      "step": 20
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 4.0220046043396,
      "learning_rate": 2.9e-05,
      "loss": 4.770322036743164,
      "step": 30
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.950177788734436,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 2.8553817749023436,
      "step": 40
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.6627838015556335,
      "learning_rate": 4.9e-05,
      "loss": 1.5436083793640136,
      "step": 50
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.30428963899612427,
      "learning_rate": 5.9e-05,
      "loss": 1.151754665374756,
      "step": 60
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 0.37808555364608765,
      "learning_rate": 6.9e-05,
      "loss": 1.1909278869628905,
      "step": 70
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.3257406949996948,
      "learning_rate": 7.900000000000001e-05,
      "loss": 0.9035618782043457,
      "step": 80
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.3209592401981354,
      "learning_rate": 8.900000000000001e-05,
      "loss": 1.085041618347168,
      "step": 90
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.38578519225120544,
      "learning_rate": 9.900000000000001e-05,
      "loss": 1.2088780403137207,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 8700778512384000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}