{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 950,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 4.845608711242676,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 2.3306,
      "step": 50
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 4.860968112945557,
      "learning_rate": 9.900000000000002e-06,
      "loss": 1.928,
      "step": 100
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 5.453705787658691,
      "learning_rate": 1.49e-05,
      "loss": 1.6681,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.570725440979004,
      "eval_runtime": 1.5119,
      "eval_samples_per_second": 1005.327,
      "eval_steps_per_second": 15.874,
      "step": 190
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 4.810089111328125,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 1.5943,
      "step": 200
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 13.012678146362305,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 1.4694,
      "step": 250
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 11.198631286621094,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 1.3752,
      "step": 300
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 9.748913764953613,
      "learning_rate": 3.49e-05,
      "loss": 1.2861,
      "step": 350
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.3308887481689453,
      "eval_runtime": 1.544,
      "eval_samples_per_second": 984.488,
      "eval_steps_per_second": 15.545,
      "step": 380
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 12.868274688720703,
      "learning_rate": 3.99e-05,
      "loss": 1.2325,
      "step": 400
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 10.431174278259277,
      "learning_rate": 4.49e-05,
      "loss": 1.0542,
      "step": 450
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 8.311651229858398,
      "learning_rate": 4.99e-05,
      "loss": 1.0175,
      "step": 500
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 22.464628219604492,
      "learning_rate": 4.4555555555555555e-05,
      "loss": 1.0534,
      "step": 550
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.2336760759353638,
      "eval_runtime": 1.5299,
      "eval_samples_per_second": 993.557,
      "eval_steps_per_second": 15.688,
      "step": 570
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 12.188404083251953,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.8699,
      "step": 600
    },
    {
      "epoch": 3.4210526315789473,
      "grad_norm": 11.911046981811523,
      "learning_rate": 3.3444444444444443e-05,
      "loss": 0.6847,
      "step": 650
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 11.840217590332031,
      "learning_rate": 2.788888888888889e-05,
      "loss": 0.7332,
      "step": 700
    },
    {
      "epoch": 3.9473684210526314,
      "grad_norm": 19.36884117126465,
      "learning_rate": 2.2333333333333335e-05,
      "loss": 0.6441,
      "step": 750
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3029890060424805,
      "eval_runtime": 1.5383,
      "eval_samples_per_second": 988.106,
      "eval_steps_per_second": 15.602,
      "step": 760
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 13.214131355285645,
      "learning_rate": 1.677777777777778e-05,
      "loss": 0.5272,
      "step": 800
    },
    {
      "epoch": 4.473684210526316,
      "grad_norm": 15.042282104492188,
      "learning_rate": 1.1222222222222224e-05,
      "loss": 0.4258,
      "step": 850
    },
    {
      "epoch": 4.7368421052631575,
      "grad_norm": 15.808998107910156,
      "learning_rate": 5.666666666666667e-06,
      "loss": 0.4341,
      "step": 900
    },
    {
      "epoch": 5.0,
      "grad_norm": 42.850643157958984,
      "learning_rate": 1.1111111111111112e-07,
      "loss": 0.4298,
      "step": 950
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.5854742527008057,
      "eval_runtime": 1.5439,
      "eval_samples_per_second": 984.541,
      "eval_steps_per_second": 15.545,
      "step": 950
    }
  ],
  "logging_steps": 50,
  "max_steps": 950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}