{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022282881176536127,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.427627058845375e-05,
      "eval_loss": 2.1343741416931152,
      "eval_runtime": 325.7647,
      "eval_samples_per_second": 17.402,
      "eval_steps_per_second": 8.703,
      "step": 1
    },
    {
      "epoch": 0.00022282881176536126,
      "grad_norm": 25.886354446411133,
      "learning_rate": 3e-05,
      "loss": 8.7004,
      "step": 3
    },
    {
      "epoch": 0.0003713813529422688,
      "eval_loss": 1.963747262954712,
      "eval_runtime": 325.0949,
      "eval_samples_per_second": 17.438,
      "eval_steps_per_second": 8.721,
      "step": 5
    },
    {
      "epoch": 0.0004456576235307225,
      "grad_norm": 22.679584503173828,
      "learning_rate": 6e-05,
      "loss": 8.3137,
      "step": 6
    },
    {
      "epoch": 0.0006684864352960838,
      "grad_norm": 11.384376525878906,
      "learning_rate": 9e-05,
      "loss": 7.3825,
      "step": 9
    },
    {
      "epoch": 0.0007427627058845376,
      "eval_loss": 1.722792387008667,
      "eval_runtime": 325.0422,
      "eval_samples_per_second": 17.441,
      "eval_steps_per_second": 8.722,
      "step": 10
    },
    {
      "epoch": 0.000891315247061445,
      "grad_norm": 15.562954902648926,
      "learning_rate": 9.755282581475769e-05,
      "loss": 6.6676,
      "step": 12
    },
    {
      "epoch": 0.0011141440588268063,
      "grad_norm": 8.043631553649902,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.2055,
      "step": 15
    },
    {
      "epoch": 0.0011141440588268063,
      "eval_loss": 1.5773813724517822,
      "eval_runtime": 325.2071,
      "eval_samples_per_second": 17.432,
      "eval_steps_per_second": 8.718,
      "step": 15
    },
    {
      "epoch": 0.0013369728705921677,
      "grad_norm": 9.106437683105469,
      "learning_rate": 6.545084971874738e-05,
      "loss": 6.2896,
      "step": 18
    },
    {
      "epoch": 0.0014855254117690751,
      "eval_loss": 1.5370134115219116,
      "eval_runtime": 325.1664,
      "eval_samples_per_second": 17.434,
      "eval_steps_per_second": 8.719,
      "step": 20
    },
    {
      "epoch": 0.0015598016823575288,
      "grad_norm": 10.149421691894531,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 6.4206,
      "step": 21
    },
    {
      "epoch": 0.00178263049412289,
      "grad_norm": 7.656150817871094,
      "learning_rate": 2.061073738537635e-05,
      "loss": 6.4307,
      "step": 24
    },
    {
      "epoch": 0.001856906764711344,
      "eval_loss": 1.5194510221481323,
      "eval_runtime": 325.1484,
      "eval_samples_per_second": 17.435,
      "eval_steps_per_second": 8.719,
      "step": 25
    },
    {
      "epoch": 0.002005459305888251,
      "grad_norm": 9.99641227722168,
      "learning_rate": 5.449673790581611e-06,
      "loss": 6.298,
      "step": 27
    },
    {
      "epoch": 0.0022282881176536127,
      "grad_norm": 10.378310203552246,
      "learning_rate": 0.0,
      "loss": 5.5548,
      "step": 30
    },
    {
      "epoch": 0.0022282881176536127,
      "eval_loss": 1.5158554315567017,
      "eval_runtime": 324.9413,
      "eval_samples_per_second": 17.446,
      "eval_steps_per_second": 8.725,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1074302287806464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}