{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 7.170517444610596,
      "learning_rate": 2.384538152610442e-06,
      "loss": 1.0465,
      "step": 25
    },
    {
      "epoch": 0.05,
      "grad_norm": 10.455423355102539,
      "learning_rate": 2.2590361445783136e-06,
      "loss": 0.7535,
      "step": 50
    },
    {
      "epoch": 0.075,
      "grad_norm": 8.283687591552734,
      "learning_rate": 2.1335341365461848e-06,
      "loss": 0.8651,
      "step": 75
    },
    {
      "epoch": 0.1,
      "grad_norm": 6.851273059844971,
      "learning_rate": 2.0080321285140564e-06,
      "loss": 0.8206,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.8211263418197632,
      "eval_runtime": 56.9885,
      "eval_samples_per_second": 1.755,
      "eval_steps_per_second": 0.228,
      "step": 100
    },
    {
      "epoch": 0.125,
      "grad_norm": 10.03593635559082,
      "learning_rate": 1.882530120481928e-06,
      "loss": 0.8954,
      "step": 125
    },
    {
      "epoch": 0.15,
      "grad_norm": 9.097064018249512,
      "learning_rate": 1.7570281124497993e-06,
      "loss": 0.7799,
      "step": 150
    },
    {
      "epoch": 0.175,
      "grad_norm": 8.4725980758667,
      "learning_rate": 1.6315261044176709e-06,
      "loss": 0.9198,
      "step": 175
    },
    {
      "epoch": 0.2,
      "grad_norm": 8.924888610839844,
      "learning_rate": 1.5060240963855425e-06,
      "loss": 0.8724,
      "step": 200
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.7925341725349426,
      "eval_runtime": 56.968,
      "eval_samples_per_second": 1.755,
      "eval_steps_per_second": 0.228,
      "step": 200
    },
    {
      "epoch": 0.225,
      "grad_norm": 6.461976051330566,
      "learning_rate": 1.3805220883534137e-06,
      "loss": 0.8322,
      "step": 225
    },
    {
      "epoch": 0.25,
      "grad_norm": 7.063958644866943,
      "learning_rate": 1.2550200803212854e-06,
      "loss": 0.861,
      "step": 250
    },
    {
      "epoch": 0.275,
      "grad_norm": 6.9858717918396,
      "learning_rate": 1.1295180722891568e-06,
      "loss": 0.7642,
      "step": 275
    },
    {
      "epoch": 0.3,
      "grad_norm": 7.707013130187988,
      "learning_rate": 1.0040160642570282e-06,
      "loss": 0.8511,
      "step": 300
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.7797713279724121,
      "eval_runtime": 56.99,
      "eval_samples_per_second": 1.755,
      "eval_steps_per_second": 0.228,
      "step": 300
    },
    {
      "epoch": 0.325,
      "grad_norm": 7.655570030212402,
      "learning_rate": 8.785140562248996e-07,
      "loss": 0.8143,
      "step": 325
    },
    {
      "epoch": 0.35,
      "grad_norm": 8.048370361328125,
      "learning_rate": 7.530120481927713e-07,
      "loss": 0.6787,
      "step": 350
    },
    {
      "epoch": 0.375,
      "grad_norm": 6.387711524963379,
      "learning_rate": 6.275100401606427e-07,
      "loss": 0.7902,
      "step": 375
    },
    {
      "epoch": 0.4,
      "grad_norm": 9.847099304199219,
      "learning_rate": 5.020080321285141e-07,
      "loss": 0.8259,
      "step": 400
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.7755066156387329,
      "eval_runtime": 56.9978,
      "eval_samples_per_second": 1.754,
      "eval_steps_per_second": 0.228,
      "step": 400
    },
    {
      "epoch": 0.425,
      "grad_norm": 8.252591133117676,
      "learning_rate": 3.7650602409638563e-07,
      "loss": 0.8635,
      "step": 425
    },
    {
      "epoch": 0.45,
      "grad_norm": 8.494077682495117,
      "learning_rate": 2.5100401606425705e-07,
      "loss": 0.68,
      "step": 450
    },
    {
      "epoch": 0.475,
      "grad_norm": 10.147363662719727,
      "learning_rate": 1.2550200803212853e-07,
      "loss": 0.7337,
      "step": 475
    },
    {
      "epoch": 0.5,
      "grad_norm": 9.55865478515625,
      "learning_rate": 0.0,
      "loss": 0.8314,
      "step": 500
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.7734402418136597,
      "eval_runtime": 56.9728,
      "eval_samples_per_second": 1.755,
      "eval_steps_per_second": 0.228,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1052597116928e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}