{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.256410256410255,
  "eval_steps": 100,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 92.9238510131836,
      "learning_rate": 9.9907e-06,
      "loss": 2.4016,
      "step": 100
    },
    {
      "epoch": 0.5128205128205128,
      "eval_loss": 2.1255013942718506,
      "eval_runtime": 34.4318,
      "eval_samples_per_second": 11.414,
      "eval_steps_per_second": 1.452,
      "step": 100
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 47.019439697265625,
      "learning_rate": 9.980700000000001e-06,
      "loss": 2.0696,
      "step": 200
    },
    {
      "epoch": 1.0256410256410255,
      "eval_loss": 1.9405728578567505,
      "eval_runtime": 34.0713,
      "eval_samples_per_second": 11.535,
      "eval_steps_per_second": 1.468,
      "step": 200
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 52.230751037597656,
      "learning_rate": 9.970700000000001e-06,
      "loss": 1.9983,
      "step": 300
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": 1.900020718574524,
      "eval_runtime": 34.1694,
      "eval_samples_per_second": 11.502,
      "eval_steps_per_second": 1.463,
      "step": 300
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 39.62374496459961,
      "learning_rate": 9.960800000000001e-06,
      "loss": 1.8888,
      "step": 400
    },
    {
      "epoch": 2.051282051282051,
      "eval_loss": 1.8164124488830566,
      "eval_runtime": 34.1213,
      "eval_samples_per_second": 11.518,
      "eval_steps_per_second": 1.465,
      "step": 400
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 39.697731018066406,
      "learning_rate": 9.9508e-06,
      "loss": 1.8456,
      "step": 500
    },
    {
      "epoch": 2.564102564102564,
      "eval_loss": 1.7753618955612183,
      "eval_runtime": 34.149,
      "eval_samples_per_second": 11.508,
      "eval_steps_per_second": 1.464,
      "step": 500
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 52.823184967041016,
      "learning_rate": 9.9408e-06,
      "loss": 1.7839,
      "step": 600
    },
    {
      "epoch": 3.076923076923077,
      "eval_loss": 1.7344136238098145,
      "eval_runtime": 34.121,
      "eval_samples_per_second": 11.518,
      "eval_steps_per_second": 1.465,
      "step": 600
    },
    {
      "epoch": 3.58974358974359,
      "grad_norm": 107.05223083496094,
      "learning_rate": 9.9308e-06,
      "loss": 1.7544,
      "step": 700
    },
    {
      "epoch": 3.58974358974359,
      "eval_loss": 1.6865615844726562,
      "eval_runtime": 34.0842,
      "eval_samples_per_second": 11.53,
      "eval_steps_per_second": 1.467,
      "step": 700
    },
    {
      "epoch": 4.102564102564102,
      "grad_norm": 53.641353607177734,
      "learning_rate": 9.9208e-06,
      "loss": 1.6812,
      "step": 800
    },
    {
      "epoch": 4.102564102564102,
      "eval_loss": 1.6568766832351685,
      "eval_runtime": 34.432,
      "eval_samples_per_second": 11.414,
      "eval_steps_per_second": 1.452,
      "step": 800
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 40.92328643798828,
      "learning_rate": 9.9109e-06,
      "loss": 1.6501,
      "step": 900
    },
    {
      "epoch": 4.615384615384615,
      "eval_loss": 1.6080188751220703,
      "eval_runtime": 34.1751,
      "eval_samples_per_second": 11.5,
      "eval_steps_per_second": 1.463,
      "step": 900
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 28.52039909362793,
      "learning_rate": 9.9009e-06,
      "loss": 1.6579,
      "step": 1000
    },
    {
      "epoch": 5.128205128205128,
      "eval_loss": 1.6059809923171997,
      "eval_runtime": 34.1634,
      "eval_samples_per_second": 11.504,
      "eval_steps_per_second": 1.464,
      "step": 1000
    },
    {
      "epoch": 5.641025641025641,
      "grad_norm": 73.21099090576172,
      "learning_rate": 9.8909e-06,
      "loss": 1.6286,
      "step": 1100
    },
    {
      "epoch": 5.641025641025641,
      "eval_loss": 1.5779187679290771,
      "eval_runtime": 34.1489,
      "eval_samples_per_second": 11.508,
      "eval_steps_per_second": 1.464,
      "step": 1100
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 36.768428802490234,
      "learning_rate": 9.8809e-06,
      "loss": 1.5871,
      "step": 1200
    },
    {
      "epoch": 6.153846153846154,
      "eval_loss": 1.5641562938690186,
      "eval_runtime": 34.1081,
      "eval_samples_per_second": 11.522,
      "eval_steps_per_second": 1.466,
      "step": 1200
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 28.098352432250977,
      "learning_rate": 9.8709e-06,
      "loss": 1.6231,
      "step": 1300
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 1.530659556388855,
      "eval_runtime": 34.0717,
      "eval_samples_per_second": 11.534,
      "eval_steps_per_second": 1.467,
      "step": 1300
    },
    {
      "epoch": 7.17948717948718,
      "grad_norm": 48.131195068359375,
      "learning_rate": 9.8609e-06,
      "loss": 1.5178,
      "step": 1400
    },
    {
      "epoch": 7.17948717948718,
      "eval_loss": 1.5207794904708862,
      "eval_runtime": 34.0224,
      "eval_samples_per_second": 11.551,
      "eval_steps_per_second": 1.47,
      "step": 1400
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 15.9362211227417,
      "learning_rate": 9.8509e-06,
      "loss": 1.5434,
      "step": 1500
    },
    {
      "epoch": 7.6923076923076925,
      "eval_loss": 1.4978805780410767,
      "eval_runtime": 34.0269,
      "eval_samples_per_second": 11.55,
      "eval_steps_per_second": 1.469,
      "step": 1500
    },
    {
      "epoch": 8.205128205128204,
      "grad_norm": 21.21210479736328,
      "learning_rate": 9.840900000000001e-06,
      "loss": 1.5368,
      "step": 1600
    },
    {
      "epoch": 8.205128205128204,
      "eval_loss": 1.4791795015335083,
      "eval_runtime": 34.5402,
      "eval_samples_per_second": 11.378,
      "eval_steps_per_second": 1.448,
      "step": 1600
    },
    {
      "epoch": 8.717948717948717,
      "grad_norm": 39.53807830810547,
      "learning_rate": 9.830900000000001e-06,
      "loss": 1.5163,
      "step": 1700
    },
    {
      "epoch": 8.717948717948717,
      "eval_loss": 1.4630368947982788,
      "eval_runtime": 34.1482,
      "eval_samples_per_second": 11.509,
      "eval_steps_per_second": 1.464,
      "step": 1700
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 42.564842224121094,
      "learning_rate": 9.820900000000001e-06,
      "loss": 1.483,
      "step": 1800
    },
    {
      "epoch": 9.23076923076923,
      "eval_loss": 1.4529582262039185,
      "eval_runtime": 34.2374,
      "eval_samples_per_second": 11.479,
      "eval_steps_per_second": 1.46,
      "step": 1800
    },
    {
      "epoch": 9.743589743589745,
      "grad_norm": 55.969017028808594,
      "learning_rate": 9.810900000000001e-06,
      "loss": 1.4795,
      "step": 1900
    },
    {
      "epoch": 9.743589743589745,
      "eval_loss": 1.4357120990753174,
      "eval_runtime": 34.2522,
      "eval_samples_per_second": 11.474,
      "eval_steps_per_second": 1.46,
      "step": 1900
    },
    {
      "epoch": 10.256410256410255,
      "grad_norm": 25.308517456054688,
      "learning_rate": 9.800900000000001e-06,
      "loss": 1.4151,
      "step": 2000
    },
    {
      "epoch": 10.256410256410255,
      "eval_loss": 1.432659387588501,
      "eval_runtime": 34.2016,
      "eval_samples_per_second": 11.491,
      "eval_steps_per_second": 1.462,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 513,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.64486332416e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}