{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 5.389516730584021,
      "learning_rate": 4.9839963190492576e-05,
      "loss": 0.7555,
      "num_input_tokens_seen": 256960,
      "step": 5,
      "train_runtime": 32.8726,
      "train_tokens_per_second": 7816.843
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 3.138977267645858,
      "learning_rate": 4.9193323673337476e-05,
      "loss": 0.4688,
      "num_input_tokens_seen": 520160,
      "step": 10,
      "train_runtime": 58.4348,
      "train_tokens_per_second": 8901.55
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 1.9755541197783468,
      "learning_rate": 4.806299712081172e-05,
      "loss": 0.4121,
      "num_input_tokens_seen": 780072,
      "step": 15,
      "train_runtime": 83.9935,
      "train_tokens_per_second": 9287.291
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 5.889624762007321,
      "learning_rate": 4.647158168051066e-05,
      "loss": 0.3846,
      "num_input_tokens_seen": 1044392,
      "step": 20,
      "train_runtime": 109.6459,
      "train_tokens_per_second": 9525.135
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 1.2235406213647593,
      "learning_rate": 4.445089385796099e-05,
      "loss": 0.3815,
      "num_input_tokens_seen": 1304776,
      "step": 25,
      "train_runtime": 134.9424,
      "train_tokens_per_second": 9669.131
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 1.0683102943611105,
      "learning_rate": 4.204133242248832e-05,
      "loss": 0.3832,
      "num_input_tokens_seen": 1570800,
      "step": 30,
      "train_runtime": 160.3739,
      "train_tokens_per_second": 9794.61
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 1.0750347246493508,
      "learning_rate": 3.929107073146197e-05,
      "loss": 0.3741,
      "num_input_tokens_seen": 1832200,
      "step": 35,
      "train_runtime": 185.7504,
      "train_tokens_per_second": 9863.772
    },
    {
      "epoch": 1.0813559322033899,
      "grad_norm": 0.8734367906334863,
      "learning_rate": 3.6255093620441834e-05,
      "loss": 0.2731,
      "num_input_tokens_seen": 2090208,
      "step": 40,
      "train_runtime": 210.3732,
      "train_tokens_per_second": 9935.716
    },
    {
      "epoch": 1.2169491525423728,
      "grad_norm": 0.8766224598320921,
      "learning_rate": 3.2994098114281134e-05,
      "loss": 0.1815,
      "num_input_tokens_seen": 2354848,
      "step": 45,
      "train_runtime": 235.7824,
      "train_tokens_per_second": 9987.38
    },
    {
      "epoch": 1.352542372881356,
      "grad_norm": 0.8177117110259531,
      "learning_rate": 2.9573279936809667e-05,
      "loss": 0.1772,
      "num_input_tokens_seen": 2613552,
      "step": 50,
      "train_runtime": 261.07,
      "train_tokens_per_second": 10010.924
    },
    {
      "epoch": 1.488135593220339,
      "grad_norm": 0.7233871182762651,
      "learning_rate": 2.606103007990371e-05,
      "loss": 0.1767,
      "num_input_tokens_seen": 2880040,
      "step": 55,
      "train_runtime": 286.582,
      "train_tokens_per_second": 10049.62
    },
    {
      "epoch": 1.623728813559322,
      "grad_norm": 0.6985657612141047,
      "learning_rate": 2.2527567490893758e-05,
      "loss": 0.1729,
      "num_input_tokens_seen": 3141872,
      "step": 60,
      "train_runtime": 312.1829,
      "train_tokens_per_second": 10064.203
    },
    {
      "epoch": 1.759322033898305,
      "grad_norm": 0.7398167457365813,
      "learning_rate": 1.904353521442088e-05,
      "loss": 0.1704,
      "num_input_tokens_seen": 3402088,
      "step": 65,
      "train_runtime": 337.3138,
      "train_tokens_per_second": 10085.824
    },
    {
      "epoch": 1.8949152542372882,
      "grad_norm": 0.7777946582004355,
      "learning_rate": 1.567858805549229e-05,
      "loss": 0.1628,
      "num_input_tokens_seen": 3663008,
      "step": 70,
      "train_runtime": 363.0243,
      "train_tokens_per_second": 10090.254
    },
    {
      "epoch": 2.0271186440677966,
      "grad_norm": 0.709214405015576,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.1438,
      "num_input_tokens_seen": 3918864,
      "step": 75,
      "train_runtime": 387.6707,
      "train_tokens_per_second": 10108.744
    },
    {
      "epoch": 2.1627118644067798,
      "grad_norm": 0.45507439489415397,
      "learning_rate": 9.571319233963627e-06,
      "loss": 0.0713,
      "num_input_tokens_seen": 4183256,
      "step": 80,
      "train_runtime": 413.1057,
      "train_tokens_per_second": 10126.357
    },
    {
      "epoch": 2.298305084745763,
      "grad_norm": 0.45196090531442223,
      "learning_rate": 6.951097651136889e-06,
      "loss": 0.0633,
      "num_input_tokens_seen": 4448016,
      "step": 85,
      "train_runtime": 438.6986,
      "train_tokens_per_second": 10139.116
    },
    {
      "epoch": 2.4338983050847456,
      "grad_norm": 0.4885688394161113,
      "learning_rate": 4.691720249402856e-06,
      "loss": 0.0599,
      "num_input_tokens_seen": 4701808,
      "step": 90,
      "train_runtime": 464.0382,
      "train_tokens_per_second": 10132.373
    },
    {
      "epoch": 2.5694915254237287,
      "grad_norm": 0.4741771649848976,
      "learning_rate": 2.8383578193475315e-06,
      "loss": 0.0574,
      "num_input_tokens_seen": 4960648,
      "step": 95,
      "train_runtime": 489.5242,
      "train_tokens_per_second": 10133.612
    },
    {
      "epoch": 2.705084745762712,
      "grad_norm": 0.43334153315557006,
      "learning_rate": 1.428063863472895e-06,
      "loss": 0.0534,
      "num_input_tokens_seen": 5224432,
      "step": 100,
      "train_runtime": 514.9998,
      "train_tokens_per_second": 10144.533
    },
    {
      "epoch": 2.840677966101695,
      "grad_norm": 0.4532410169042894,
      "learning_rate": 4.890338009668316e-07,
      "loss": 0.0536,
      "num_input_tokens_seen": 5489120,
      "step": 105,
      "train_runtime": 754.9559,
      "train_tokens_per_second": 7270.782
    },
    {
      "epoch": 2.976271186440678,
      "grad_norm": 0.484714255010592,
      "learning_rate": 4.004126844042444e-08,
      "loss": 0.0559,
      "num_input_tokens_seen": 5751896,
      "step": 110,
      "train_runtime": 780.4575,
      "train_tokens_per_second": 7369.903
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 5798376,
      "step": 111,
      "total_flos": 11582938693632.0,
      "train_loss": 0.22720730056365332,
      "train_runtime": 933.6635,
      "train_samples_per_second": 7.583,
      "train_steps_per_second": 0.119
    }
  ],
  "logging_steps": 5,
  "max_steps": 111,
  "num_input_tokens_seen": 5798376,
  "num_train_epochs": 3,
  "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": 11582938693632.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}