{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.3769792318344116,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3107,
      "mean_token_accuracy": 0.9287307560443878,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.26893970370292664,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2756,
      "mean_token_accuracy": 0.9344838559627533,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.15078027546405792,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.2688,
      "mean_token_accuracy": 0.9306879937648773,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.1351465880870819,
      "learning_rate": 0.00019984268150178167,
      "loss": 0.2451,
      "mean_token_accuracy": 0.9370594084262848,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.14794091880321503,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.1416,
      "mean_token_accuracy": 0.9599717617034912,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.12860107421875,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.1071,
      "mean_token_accuracy": 0.9663936257362366,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.12796033918857574,
      "learning_rate": 0.00018884456359788724,
      "loss": 0.0581,
      "mean_token_accuracy": 0.979266232252121,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08177585899829865,
      "learning_rate": 0.00018155608689592604,
      "loss": 0.0449,
      "mean_token_accuracy": 0.98313889503479,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.06311054527759552,
      "learning_rate": 0.0001726660322034027,
      "loss": 0.0378,
      "mean_token_accuracy": 0.9852405071258545,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.07140650600194931,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.0332,
      "mean_token_accuracy": 0.9863865613937378,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.09618227928876877,
      "learning_rate": 0.00015080753452465296,
      "loss": 0.0328,
      "mean_token_accuracy": 0.9867150962352753,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.07409857958555222,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0303,
      "mean_token_accuracy": 0.9873311817646027,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0733385905623436,
      "learning_rate": 0.0001249776478167227,
      "loss": 0.0312,
      "mean_token_accuracy": 0.9869321703910827,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.05522334575653076,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.0276,
      "mean_token_accuracy": 0.9882255017757415,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.05922674387693405,
      "learning_rate": 9.719537437241312e-05,
      "loss": 0.0279,
      "mean_token_accuracy": 0.9881398558616639,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.08130958676338196,
      "learning_rate": 8.324937766952638e-05,
      "loss": 0.027,
      "mean_token_accuracy": 0.9887233972549438,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.052543755620718,
      "learning_rate": 6.963232548903853e-05,
      "loss": 0.0251,
      "mean_token_accuracy": 0.9895359516143799,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.06618787348270416,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.0249,
      "mean_token_accuracy": 0.9895861744880676,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.042255669832229614,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.0262,
      "mean_token_accuracy": 0.9887180864810944,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.04344850778579712,
      "learning_rate": 3.336534220479961e-05,
      "loss": 0.026,
      "mean_token_accuracy": 0.988743656873703,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.05336128920316696,
      "learning_rate": 2.3596262417839255e-05,
      "loss": 0.027,
      "mean_token_accuracy": 0.9886524379253387,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.04427241161465645,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.0264,
      "mean_token_accuracy": 0.9887325942516327,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.05719885602593422,
      "learning_rate": 8.72167349386811e-06,
      "loss": 0.0246,
      "mean_token_accuracy": 0.989437359571457,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.05920225381851196,
      "learning_rate": 3.908267805490051e-06,
      "loss": 0.0248,
      "mean_token_accuracy": 0.9892986714839935,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.052159372717142105,
      "learning_rate": 9.818874663554357e-07,
      "loss": 0.0245,
      "mean_token_accuracy": 0.9898675382137299,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.040659721940755844,
      "learning_rate": 0.0,
      "loss": 0.0244,
      "mean_token_accuracy": 0.9897443354129791,
      "step": 125
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 1.7762889804808192e+16,
      "train_loss": 0.06599626523256302,
      "train_runtime": 280.6621,
      "train_samples_per_second": 3.563,
      "train_steps_per_second": 0.445
    }
  ],
  "logging_steps": 5,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7762889804808192e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}