{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8813559322033897,
  "eval_steps": 500,
  "global_step": 116,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 1.030324124303403,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.4959,
      "mean_token_accuracy": 0.8713347434997558,
      "step": 5
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.5717467306853743,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.4216,
      "mean_token_accuracy": 0.8822458744049072,
      "step": 10
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 0.30670252885331056,
      "learning_rate": 4.9907672546384545e-05,
      "loss": 0.3837,
      "mean_token_accuracy": 0.8890745401382446,
      "step": 15
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.28508850602109415,
      "learning_rate": 4.9346190892086174e-05,
      "loss": 0.3635,
      "mean_token_accuracy": 0.8940897285938263,
      "step": 20
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.231083779269082,
      "learning_rate": 4.8287289481503954e-05,
      "loss": 0.3489,
      "mean_token_accuracy": 0.8982042372226715,
      "step": 25
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2246638901095726,
      "learning_rate": 4.675507862678257e-05,
      "loss": 0.346,
      "mean_token_accuracy": 0.8966788053512573,
      "step": 30
    },
    {
      "epoch": 1.1694915254237288,
      "grad_norm": 0.22838220228380773,
      "learning_rate": 4.478444550590631e-05,
      "loss": 0.2887,
      "mean_token_accuracy": 0.9111442804336548,
      "step": 35
    },
    {
      "epoch": 1.3389830508474576,
      "grad_norm": 0.23878993019310235,
      "learning_rate": 4.2420259810417894e-05,
      "loss": 0.2754,
      "mean_token_accuracy": 0.9148677706718444,
      "step": 40
    },
    {
      "epoch": 1.5084745762711864,
      "grad_norm": 0.16810576615741815,
      "learning_rate": 3.9716352099533276e-05,
      "loss": 0.2806,
      "mean_token_accuracy": 0.9128606796264649,
      "step": 45
    },
    {
      "epoch": 1.6779661016949152,
      "grad_norm": 0.2005840241516876,
      "learning_rate": 3.6734288122687036e-05,
      "loss": 0.2748,
      "mean_token_accuracy": 0.9143766462802887,
      "step": 50
    },
    {
      "epoch": 1.847457627118644,
      "grad_norm": 0.19954679142899281,
      "learning_rate": 3.354196701817348e-05,
      "loss": 0.2685,
      "mean_token_accuracy": 0.9158895432949066,
      "step": 55
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.35183907693360755,
      "learning_rate": 3.021207530574477e-05,
      "loss": 0.2616,
      "mean_token_accuracy": 0.9172095722622342,
      "step": 60
    },
    {
      "epoch": 2.169491525423729,
      "grad_norm": 0.22105077779359006,
      "learning_rate": 2.6820431874480006e-05,
      "loss": 0.2095,
      "mean_token_accuracy": 0.9329459547996521,
      "step": 65
    },
    {
      "epoch": 2.3389830508474576,
      "grad_norm": 0.19846361542341748,
      "learning_rate": 2.344426164918712e-05,
      "loss": 0.2033,
      "mean_token_accuracy": 0.9337680399417877,
      "step": 70
    },
    {
      "epoch": 2.5084745762711864,
      "grad_norm": 0.18894701230706007,
      "learning_rate": 2.0160437242530445e-05,
      "loss": 0.1939,
      "mean_token_accuracy": 0.937131541967392,
      "step": 75
    },
    {
      "epoch": 2.6779661016949152,
      "grad_norm": 0.20211452980324235,
      "learning_rate": 1.704372862901521e-05,
      "loss": 0.1914,
      "mean_token_accuracy": 0.9378842771053314,
      "step": 80
    },
    {
      "epoch": 2.847457627118644,
      "grad_norm": 0.1894485868510866,
      "learning_rate": 1.4165100694309626e-05,
      "loss": 0.1949,
      "mean_token_accuracy": 0.9367973864078522,
      "step": 85
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2043299022821172,
      "learning_rate": 1.1590097423302684e-05,
      "loss": 0.1836,
      "mean_token_accuracy": 0.9393455651071336,
      "step": 90
    },
    {
      "epoch": 3.169491525423729,
      "grad_norm": 0.1901039140832894,
      "learning_rate": 9.377349517603714e-06,
      "loss": 0.1444,
      "mean_token_accuracy": 0.9531322956085205,
      "step": 95
    },
    {
      "epoch": 3.3389830508474576,
      "grad_norm": 0.17816548408646005,
      "learning_rate": 7.57723942280278e-06,
      "loss": 0.1399,
      "mean_token_accuracy": 0.9542467951774597,
      "step": 100
    },
    {
      "epoch": 3.5084745762711864,
      "grad_norm": 0.202508229530206,
      "learning_rate": 6.230754161720593e-06,
      "loss": 0.1377,
      "mean_token_accuracy": 0.9551035225391388,
      "step": 105
    },
    {
      "epoch": 3.6779661016949152,
      "grad_norm": 0.18079082215089404,
      "learning_rate": 5.368552093689271e-06,
      "loss": 0.1365,
      "mean_token_accuracy": 0.9550769627094269,
      "step": 110
    },
    {
      "epoch": 3.847457627118644,
      "grad_norm": 0.18036470362534995,
      "learning_rate": 5.010264848985499e-06,
      "loss": 0.1337,
      "mean_token_accuracy": 0.9559988558292389,
      "step": 115
    },
    {
      "epoch": 3.8813559322033897,
      "mean_token_accuracy": 0.9553212523460388,
      "step": 116,
      "total_flos": 55862298214400.0,
      "train_loss": 0.25453417761058644,
      "train_runtime": 699.0514,
      "train_samples_per_second": 2.666,
      "train_steps_per_second": 0.166
    }
  ],
  "logging_steps": 5,
  "max_steps": 116,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 55862298214400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}