{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 5.625,
      "learning_rate": 8.572335756456368e-06,
      "loss": 0.2415,
      "step": 5
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.140625,
      "learning_rate": 1.9287755452026826e-05,
      "loss": 0.1367,
      "step": 10
    },
    {
      "epoch": 0.075,
      "grad_norm": 2.859375,
      "learning_rate": 3.000317514759729e-05,
      "loss": 0.1025,
      "step": 15
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.21875,
      "learning_rate": 4.071859484316775e-05,
      "loss": 0.0911,
      "step": 20
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.6953125,
      "learning_rate": 5.143401453873821e-05,
      "loss": 0.0852,
      "step": 25
    },
    {
      "epoch": 0.15,
      "grad_norm": 3.765625,
      "learning_rate": 6.214943423430867e-05,
      "loss": 0.0845,
      "step": 30
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.80078125,
      "learning_rate": 7.286485392987913e-05,
      "loss": 0.0843,
      "step": 35
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.515625,
      "learning_rate": 7.500098100637213e-05,
      "loss": 0.0861,
      "step": 40
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.82421875,
      "learning_rate": 7.497272464974502e-05,
      "loss": 0.0792,
      "step": 45
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.78515625,
      "learning_rate": 7.492275581730845e-05,
      "loss": 0.0796,
      "step": 50
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.68359375,
      "learning_rate": 7.485111312922398e-05,
      "loss": 0.077,
      "step": 55
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.56640625,
      "learning_rate": 7.475785195705139e-05,
      "loss": 0.0763,
      "step": 60
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.69921875,
      "learning_rate": 7.464304438095277e-05,
      "loss": 0.0754,
      "step": 65
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.609375,
      "learning_rate": 7.450677913398279e-05,
      "loss": 0.0749,
      "step": 70
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.46484375,
      "learning_rate": 7.434916153350836e-05,
      "loss": 0.0744,
      "step": 75
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.81640625,
      "learning_rate": 7.417031339981032e-05,
      "loss": 0.0784,
      "step": 80
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.57421875,
      "learning_rate": 7.397037296193046e-05,
      "loss": 0.0773,
      "step": 85
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.55078125,
      "learning_rate": 7.374949475083626e-05,
      "loss": 0.0744,
      "step": 90
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.53125,
      "learning_rate": 7.350784947998634e-05,
      "loss": 0.0736,
      "step": 95
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.51953125,
      "learning_rate": 7.324562391338845e-05,
      "loss": 0.0729,
      "step": 100
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.578125,
      "learning_rate": 7.296302072125253e-05,
      "loss": 0.0735,
      "step": 105
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.75,
      "learning_rate": 7.266025832334978e-05,
      "loss": 0.0738,
      "step": 110
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.5390625,
      "learning_rate": 7.233757072019941e-05,
      "loss": 0.0735,
      "step": 115
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.59375,
      "learning_rate": 7.19952073122131e-05,
      "loss": 0.0715,
      "step": 120
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.671875,
      "learning_rate": 7.163343270693716e-05,
      "loss": 0.0696,
      "step": 125
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5,
      "learning_rate": 7.125252651454133e-05,
      "loss": 0.0697,
      "step": 130
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.66015625,
      "learning_rate": 7.085278313171226e-05,
      "loss": 0.0697,
      "step": 135
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.56640625,
      "learning_rate": 7.043451151411875e-05,
      "loss": 0.0677,
      "step": 140
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.53125,
      "learning_rate": 6.999803493762452e-05,
      "loss": 0.0711,
      "step": 145
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.55078125,
      "learning_rate": 6.954369074843315e-05,
      "loss": 0.0712,
      "step": 150
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.515625,
      "learning_rate": 6.907183010235823e-05,
      "loss": 0.0715,
      "step": 155
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.453125,
      "learning_rate": 6.858281769342038e-05,
      "loss": 0.0715,
      "step": 160
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.482421875,
      "learning_rate": 6.807703147198056e-05,
      "loss": 0.0699,
      "step": 165
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.50390625,
      "learning_rate": 6.755486235262808e-05,
      "loss": 0.0686,
      "step": 170
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.515625,
      "learning_rate": 6.701671391204843e-05,
      "loss": 0.0681,
      "step": 175
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.66796875,
      "learning_rate": 6.646300207710494e-05,
      "loss": 0.0683,
      "step": 180
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.44921875,
      "learning_rate": 6.589415480337521e-05,
      "loss": 0.0663,
      "step": 185
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.412109375,
      "learning_rate": 6.531061174439061e-05,
      "loss": 0.0685,
      "step": 190
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.38671875,
      "learning_rate": 6.471282391183463e-05,
      "loss": 0.0662,
      "step": 195
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.42578125,
      "learning_rate": 6.410125332696272e-05,
      "loss": 0.0675,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.06526587158441544,
      "eval_runtime": 1.0744,
      "eval_samples_per_second": 22.339,
      "eval_steps_per_second": 22.339,
      "step": 200
    },
    {
      "epoch": 1.025,
      "grad_norm": 0.453125,
      "learning_rate": 6.347637266351305e-05,
      "loss": 0.0581,
      "step": 205
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.5078125,
      "learning_rate": 6.2838664882384e-05,
      "loss": 0.057,
      "step": 210
    },
    {
      "epoch": 1.075,
      "grad_norm": 0.44921875,
      "learning_rate": 6.218862285836094e-05,
      "loss": 0.0587,
      "step": 215
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.447265625,
      "learning_rate": 6.152674899918066e-05,
      "loss": 0.0558,
      "step": 220
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.53125,
      "learning_rate": 6.085355485722805e-05,
      "loss": 0.0579,
      "step": 225
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.43359375,
      "learning_rate": 6.016956073416482e-05,
      "loss": 0.059,
      "step": 230
    },
    {
      "epoch": 1.175,
      "grad_norm": 0.61328125,
      "learning_rate": 5.9475295278796255e-05,
      "loss": 0.0587,
      "step": 235
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.380859375,
      "learning_rate": 5.877129507848637e-05,
      "loss": 0.0593,
      "step": 240
    },
    {
      "epoch": 1.225,
      "grad_norm": 0.50390625,
      "learning_rate": 5.805810424443765e-05,
      "loss": 0.0584,
      "step": 245
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.484375,
      "learning_rate": 5.733627399115563e-05,
      "loss": 0.0592,
      "step": 250
    },
    {
      "epoch": 1.275,
      "grad_norm": 0.5078125,
      "learning_rate": 5.66063622104235e-05,
      "loss": 0.057,
      "step": 255
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.48046875,
      "learning_rate": 5.586893304011584e-05,
      "loss": 0.0573,
      "step": 260
    },
    {
      "epoch": 1.325,
      "grad_norm": 0.486328125,
      "learning_rate": 5.512455642818499e-05,
      "loss": 0.0583,
      "step": 265
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.4453125,
      "learning_rate": 5.4373807692156764e-05,
      "loss": 0.058,
      "step": 270
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.421875,
      "learning_rate": 5.36172670744762e-05,
      "loss": 0.0575,
      "step": 275
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.369140625,
      "learning_rate": 5.285551929404679e-05,
      "loss": 0.0551,
      "step": 280
    },
    {
      "epoch": 1.425,
      "grad_norm": 0.412109375,
      "learning_rate": 5.208915309431016e-05,
      "loss": 0.0573,
      "step": 285
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.453125,
      "learning_rate": 5.13187607882149e-05,
      "loss": 0.059,
      "step": 290
    },
    {
      "epoch": 1.475,
      "grad_norm": 0.35546875,
      "learning_rate": 5.0544937800426944e-05,
      "loss": 0.0579,
      "step": 295
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.484375,
      "learning_rate": 4.976828220713459e-05,
      "loss": 0.0562,
      "step": 300
    },
    {
      "epoch": 1.525,
      "grad_norm": 0.443359375,
      "learning_rate": 4.8989394273804545e-05,
      "loss": 0.057,
      "step": 305
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.36328125,
      "learning_rate": 4.820887599124563e-05,
      "loss": 0.0572,
      "step": 310
    },
    {
      "epoch": 1.575,
      "grad_norm": 0.41015625,
      "learning_rate": 4.7427330610339186e-05,
      "loss": 0.0562,
      "step": 315
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.416015625,
      "learning_rate": 4.66453621757954e-05,
      "loss": 0.0561,
      "step": 320
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.373046875,
      "learning_rate": 4.5863575059296397e-05,
      "loss": 0.0574,
      "step": 325
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.44921875,
      "learning_rate": 4.508257349238615e-05,
      "loss": 0.059,
      "step": 330
    },
    {
      "epoch": 1.675,
      "grad_norm": 0.46484375,
      "learning_rate": 4.4302961099469247e-05,
      "loss": 0.0559,
      "step": 335
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.369140625,
      "learning_rate": 4.352534043127848e-05,
      "loss": 0.0567,
      "step": 340
    },
    {
      "epoch": 1.725,
      "grad_norm": 0.46484375,
      "learning_rate": 4.275031249917243e-05,
      "loss": 0.0548,
      "step": 345
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.396484375,
      "learning_rate": 4.197847631062287e-05,
      "loss": 0.0583,
      "step": 350
    },
    {
      "epoch": 1.775,
      "grad_norm": 0.4296875,
      "learning_rate": 4.121042840625079e-05,
      "loss": 0.0548,
      "step": 355
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.33984375,
      "learning_rate": 4.044676239876911e-05,
      "loss": 0.055,
      "step": 360
    },
    {
      "epoch": 1.825,
      "grad_norm": 0.365234375,
      "learning_rate": 3.9688068514188365e-05,
      "loss": 0.0549,
      "step": 365
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.486328125,
      "learning_rate": 3.893493313563978e-05,
      "loss": 0.0552,
      "step": 370
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.37109375,
      "learning_rate": 3.8187938350168616e-05,
      "loss": 0.0554,
      "step": 375
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.59375,
      "learning_rate": 3.744766149884778e-05,
      "loss": 0.0563,
      "step": 380
    },
    {
      "epoch": 1.925,
      "grad_norm": 0.396484375,
      "learning_rate": 3.671467473055956e-05,
      "loss": 0.0552,
      "step": 385
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.361328125,
      "learning_rate": 3.598954455979035e-05,
      "loss": 0.0555,
      "step": 390
    },
    {
      "epoch": 1.975,
      "grad_norm": 0.37890625,
      "learning_rate": 3.52728314287801e-05,
      "loss": 0.0565,
      "step": 395
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.390625,
      "learning_rate": 3.4565089274364856e-05,
      "loss": 0.0541,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.06434744596481323,
      "eval_runtime": 0.9755,
      "eval_samples_per_second": 24.602,
      "eval_steps_per_second": 24.602,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.46279712014336e+17,
  "train_batch_size": 140,
  "trial_name": null,
  "trial_params": null
}