{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.473684210526316,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 31.074975967407227,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.6413,
      "step": 1
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 31.317493438720703,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.6669,
      "step": 2
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 30.651592254638672,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.6365,
      "step": 3
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 31.409021377563477,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.6506,
      "step": 4
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 31.246355056762695,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.6921,
      "step": 5
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 31.102157592773438,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.6521,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 31.102157592773438,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.6507,
      "step": 7
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 51.65867233276367,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.609,
      "step": 8
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 31.440189361572266,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.6483,
      "step": 9
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 31.163721084594727,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.5929,
      "step": 10
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 31.317119598388672,
      "learning_rate": 5.5e-07,
      "loss": 2.622,
      "step": 11
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 30.929079055786133,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.5431,
      "step": 12
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 31.02151107788086,
      "learning_rate": 6.5e-07,
      "loss": 2.4984,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 31.02151107788086,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.4068,
      "step": 14
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 49.92241287231445,
      "learning_rate": 7.5e-07,
      "loss": 2.4271,
      "step": 15
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 30.406696319580078,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.3558,
      "step": 16
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 29.96433448791504,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.2551,
      "step": 17
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 29.700254440307617,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.1759,
      "step": 18
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 29.448490142822266,
      "learning_rate": 9.500000000000001e-07,
      "loss": 2.0745,
      "step": 19
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 29.727752685546875,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.8556,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 46.51616668701172,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.8905,
      "step": 21
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 26.882614135742188,
      "learning_rate": 1.1e-06,
      "loss": 1.6956,
      "step": 22
    },
    {
      "epoch": 3.3157894736842106,
      "grad_norm": 26.3736629486084,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.5783,
      "step": 23
    },
    {
      "epoch": 3.473684210526316,
      "grad_norm": 25.254058837890625,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.4137,
      "step": 24
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4153003265750467e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}