{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 7352.2265625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 175.5381,
      "step": 25
    },
    {
      "epoch": 0.025,
      "grad_norm": 2155.41015625,
      "learning_rate": 3.266666666666667e-05,
      "loss": 174.6277,
      "step": 50
    },
    {
      "epoch": 0.0375,
      "grad_norm": 29.340621948242188,
      "learning_rate": 4.933333333333334e-05,
      "loss": 157.9852,
      "step": 75
    },
    {
      "epoch": 0.05,
      "grad_norm": 11.753185272216797,
      "learning_rate": 6.6e-05,
      "loss": 133.1257,
      "step": 100
    },
    {
      "epoch": 0.05,
      "eval_accuracy": 0.08756986554511534,
      "eval_loss": 7.706512928009033,
      "eval_runtime": 7.3236,
      "eval_samples_per_second": 66.224,
      "eval_steps_per_second": 2.185,
      "step": 100
    },
    {
      "epoch": 0.0625,
      "grad_norm": 11.1610746383667,
      "learning_rate": 8.266666666666667e-05,
      "loss": 119.0136,
      "step": 125
    },
    {
      "epoch": 0.075,
      "grad_norm": 7.337241172790527,
      "learning_rate": 9.933333333333334e-05,
      "loss": 113.2304,
      "step": 150
    },
    {
      "epoch": 0.0875,
      "grad_norm": 9.895074844360352,
      "learning_rate": 9.995847987378953e-05,
      "loss": 109.5068,
      "step": 175
    },
    {
      "epoch": 0.1,
      "grad_norm": 8.935585975646973,
      "learning_rate": 9.982700328363471e-05,
      "loss": 107.0186,
      "step": 200
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.13644318107230674,
      "eval_loss": 6.609853267669678,
      "eval_runtime": 7.4218,
      "eval_samples_per_second": 65.348,
      "eval_steps_per_second": 2.156,
      "step": 200
    },
    {
      "epoch": 0.1125,
      "grad_norm": 17.207761764526367,
      "learning_rate": 9.96057350657239e-05,
      "loss": 105.3798,
      "step": 225
    },
    {
      "epoch": 0.125,
      "grad_norm": 37.589744567871094,
      "learning_rate": 9.929507396034141e-05,
      "loss": 103.9933,
      "step": 250
    },
    {
      "epoch": 0.1375,
      "grad_norm": 48.09913635253906,
      "learning_rate": 9.889557979979694e-05,
      "loss": 103.0857,
      "step": 275
    },
    {
      "epoch": 0.15,
      "grad_norm": 18.950061798095703,
      "learning_rate": 9.840797249956985e-05,
      "loss": 102.3462,
      "step": 300
    },
    {
      "epoch": 0.15,
      "eval_accuracy": 0.14476797317970908,
      "eval_loss": 6.367699146270752,
      "eval_runtime": 7.5111,
      "eval_samples_per_second": 64.571,
      "eval_steps_per_second": 2.13,
      "step": 300
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.006672071458816e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}