{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 0.03571677762600531,
      "learning_rate": 2.5e-05,
      "loss": 0.0406,
      "step": 1
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.03124717230543411,
      "learning_rate": 5e-05,
      "loss": 0.0511,
      "step": 2
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.030383068450580312,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0477,
      "step": 3
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.05095327548849085,
      "learning_rate": 0.0001,
      "loss": 0.088,
      "step": 4
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.03203811671096965,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0539,
      "step": 5
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.033726291244377225,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0397,
      "step": 6
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.023078232534599976,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0306,
      "step": 7
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.07517583677244086,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1508,
      "step": 8
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.049366663767698334,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0811,
      "step": 9
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.02779301147431827,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0459,
      "step": 10
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.04363887675102027,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0316,
      "step": 11
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0541814687973494,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0206,
      "step": 12
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.05174915093419624,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0672,
      "step": 13
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.05482383645784057,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0735,
      "step": 14
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.06684196217996566,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0552,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.05005217450797381,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0622,
      "step": 16
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0675720822616986,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0451,
      "step": 17
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.05646174028542288,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0654,
      "step": 18
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.0674228525141844,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0747,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.05489227729910441,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0747,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.059718240052461624,
      "eval_runtime": 0.4115,
      "eval_samples_per_second": 2.43,
      "eval_steps_per_second": 2.43,
      "step": 20
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.03828581474518023,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0249,
      "step": 21
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.048817392083604694,
      "learning_rate": 5e-05,
      "loss": 0.0628,
      "step": 22
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.0464271342369185,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0285,
      "step": 23
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.043564367886343436,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0299,
      "step": 24
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.05095324792104344,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0305,
      "step": 25
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.05974150824308453,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0383,
      "step": 26
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.041576889861458216,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0236,
      "step": 27
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.025309604974394218,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0104,
      "step": 28
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.04891136241795408,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0174,
      "step": 29
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.06509734010765389,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0373,
      "step": 30
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.06298170813970179,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0473,
      "step": 31
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.023456119760532017,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0116,
      "step": 32
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.0904474942760358,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0576,
      "step": 33
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.05674354282280123,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0226,
      "step": 34
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.06640866033948213,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0415,
      "step": 35
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.019382095490173296,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0145,
      "step": 36
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.06740471663162713,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0393,
      "step": 37
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.05090364013587484,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0185,
      "step": 38
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.060050091778606596,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0338,
      "step": 39
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.062448181270198404,
      "learning_rate": 0.0,
      "loss": 0.041,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.06238709017634392,
      "eval_runtime": 1.5569,
      "eval_samples_per_second": 0.642,
      "eval_steps_per_second": 0.642,
      "step": 40
    },
    {
      "epoch": 2.0,
      "step": 40,
      "total_flos": 1173388443648.0,
      "train_loss": 0.04577095708809793,
      "train_runtime": 173.9309,
      "train_samples_per_second": 0.46,
      "train_steps_per_second": 0.23
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1173388443648.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}