{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08688097306689835,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017376194613379669,
      "eval_loss": 6.652885437011719,
      "eval_runtime": 2.6405,
      "eval_samples_per_second": 92.028,
      "eval_steps_per_second": 46.203,
      "step": 1
    },
    {
      "epoch": 0.008688097306689836,
      "grad_norm": 4713.6005859375,
      "learning_rate": 5e-05,
      "loss": 27.0279,
      "step": 5
    },
    {
      "epoch": 0.01737619461337967,
      "grad_norm": 4841.03955078125,
      "learning_rate": 0.0001,
      "loss": 26.4966,
      "step": 10
    },
    {
      "epoch": 0.01737619461337967,
      "eval_loss": 6.604281425476074,
      "eval_runtime": 1.6508,
      "eval_samples_per_second": 147.206,
      "eval_steps_per_second": 73.906,
      "step": 10
    },
    {
      "epoch": 0.026064291920069503,
      "grad_norm": 6471.283203125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 26.1516,
      "step": 15
    },
    {
      "epoch": 0.03475238922675934,
      "grad_norm": 5566.80908203125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 25.9504,
      "step": 20
    },
    {
      "epoch": 0.03475238922675934,
      "eval_loss": 6.513936519622803,
      "eval_runtime": 1.6905,
      "eval_samples_per_second": 143.742,
      "eval_steps_per_second": 72.167,
      "step": 20
    },
    {
      "epoch": 0.043440486533449174,
      "grad_norm": 4252.45458984375,
      "learning_rate": 6.91341716182545e-05,
      "loss": 26.1708,
      "step": 25
    },
    {
      "epoch": 0.052128583840139006,
      "grad_norm": 3892.208740234375,
      "learning_rate": 5e-05,
      "loss": 26.0941,
      "step": 30
    },
    {
      "epoch": 0.052128583840139006,
      "eval_loss": 6.443342685699463,
      "eval_runtime": 1.7024,
      "eval_samples_per_second": 142.739,
      "eval_steps_per_second": 71.663,
      "step": 30
    },
    {
      "epoch": 0.060816681146828845,
      "grad_norm": 4265.82373046875,
      "learning_rate": 3.086582838174551e-05,
      "loss": 25.3217,
      "step": 35
    },
    {
      "epoch": 0.06950477845351868,
      "grad_norm": 3242.72119140625,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 25.3607,
      "step": 40
    },
    {
      "epoch": 0.06950477845351868,
      "eval_loss": 6.420129776000977,
      "eval_runtime": 1.6872,
      "eval_samples_per_second": 144.022,
      "eval_steps_per_second": 72.307,
      "step": 40
    },
    {
      "epoch": 0.07819287576020852,
      "grad_norm": 3691.49462890625,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 25.7192,
      "step": 45
    },
    {
      "epoch": 0.08688097306689835,
      "grad_norm": 4117.0908203125,
      "learning_rate": 0.0,
      "loss": 25.7918,
      "step": 50
    },
    {
      "epoch": 0.08688097306689835,
      "eval_loss": 6.41416072845459,
      "eval_runtime": 1.7003,
      "eval_samples_per_second": 142.919,
      "eval_steps_per_second": 71.753,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11014275858432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}