{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "grad_norm": 56.94092287577408,
      "learning_rate": 1.25e-05,
      "loss": 10.5002,
      "step": 1
    },
    {
      "epoch": 0.25,
      "grad_norm": 55.337587139972584,
      "learning_rate": 2.5e-05,
      "loss": 10.6723,
      "step": 2
    },
    {
      "epoch": 0.375,
      "grad_norm": 96.41112358646679,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 8.4987,
      "step": 3
    },
    {
      "epoch": 0.5,
      "grad_norm": 7.212661079496828,
      "learning_rate": 5e-05,
      "loss": 1.5881,
      "step": 4
    },
    {
      "epoch": 0.625,
      "grad_norm": 79.52129989219452,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 1.4161,
      "step": 5
    },
    {
      "epoch": 0.75,
      "grad_norm": 5.638528950384957,
      "learning_rate": 4.722222222222222e-05,
      "loss": 1.3169,
      "step": 6
    },
    {
      "epoch": 0.875,
      "grad_norm": 3.724084864285414,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.1448,
      "step": 7
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9023689410655398,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0803,
      "step": 8
    },
    {
      "epoch": 1.125,
      "grad_norm": 1.961911531893411,
      "learning_rate": 4.305555555555556e-05,
      "loss": 1.0115,
      "step": 9
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.7376233350994494,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.9635,
      "step": 10
    },
    {
      "epoch": 1.375,
      "grad_norm": 1.3012833795187553,
      "learning_rate": 4.027777777777778e-05,
      "loss": 0.8767,
      "step": 11
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.1428766168944244,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.7648,
      "step": 12
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.9249871747052298,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.8018,
      "step": 13
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.9222317477611536,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.7303,
      "step": 14
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.9869030389279764,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.8559,
      "step": 15
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7505289808609725,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7473,
      "step": 16
    },
    {
      "epoch": 2.125,
      "grad_norm": 0.6877680430305975,
      "learning_rate": 3.194444444444444e-05,
      "loss": 0.6932,
      "step": 17
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.6489145420320495,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.6715,
      "step": 18
    },
    {
      "epoch": 2.375,
      "grad_norm": 0.5525985803618135,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.6487,
      "step": 19
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.48284459313077943,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.5881,
      "step": 20
    },
    {
      "epoch": 2.625,
      "grad_norm": 0.4922181600547385,
      "learning_rate": 2.6388888888888892e-05,
      "loss": 0.6705,
      "step": 21
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.48437618995002524,
      "learning_rate": 2.5e-05,
      "loss": 0.6984,
      "step": 22
    },
    {
      "epoch": 2.875,
      "grad_norm": 0.4015526748931537,
      "learning_rate": 2.361111111111111e-05,
      "loss": 0.6021,
      "step": 23
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3765862829569743,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6495,
      "step": 24
    },
    {
      "epoch": 3.125,
      "grad_norm": 0.3724792221112522,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.6082,
      "step": 25
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.399419700674504,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.5776,
      "step": 26
    },
    {
      "epoch": 3.375,
      "grad_norm": 0.4271036355666931,
      "learning_rate": 1.8055555555555555e-05,
      "loss": 0.4848,
      "step": 27
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.36781128148625003,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5648,
      "step": 28
    },
    {
      "epoch": 3.625,
      "grad_norm": 0.3050256902856378,
      "learning_rate": 1.527777777777778e-05,
      "loss": 0.5301,
      "step": 29
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.34042591766070973,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.5813,
      "step": 30
    },
    {
      "epoch": 3.875,
      "grad_norm": 0.3056337381942204,
      "learning_rate": 1.25e-05,
      "loss": 0.5843,
      "step": 31
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3282149138644664,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.485,
      "step": 32
    },
    {
      "epoch": 4.125,
      "grad_norm": 0.3586326739916488,
      "learning_rate": 9.722222222222223e-06,
      "loss": 0.4799,
      "step": 33
    },
    {
      "epoch": 4.25,
      "grad_norm": 0.3323864715502126,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.5,
      "step": 34
    },
    {
      "epoch": 4.375,
      "grad_norm": 0.3160055292851411,
      "learning_rate": 6.944444444444445e-06,
      "loss": 0.5231,
      "step": 35
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.24514408833673965,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.4615,
      "step": 36
    },
    {
      "epoch": 4.625,
      "grad_norm": 0.23634195926376228,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.4654,
      "step": 37
    },
    {
      "epoch": 4.75,
      "grad_norm": 0.2831859298508377,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.5187,
      "step": 38
    },
    {
      "epoch": 4.875,
      "grad_norm": 0.3062832468306899,
      "learning_rate": 1.388888888888889e-06,
      "loss": 0.525,
      "step": 39
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.27572553234384123,
      "learning_rate": 0.0,
      "loss": 0.4395,
      "step": 40
    },
    {
      "epoch": 5.0,
      "step": 40,
      "total_flos": 3.538102688384287e+17,
      "train_loss": 1.413003572076559,
      "train_runtime": 2583.9828,
      "train_samples_per_second": 0.244,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "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": 3.538102688384287e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}