{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 19251,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025972676744065244,
      "grad_norm": 5.497185230255127,
      "learning_rate": 1.9480546465118697e-05,
      "loss": 1.798,
      "step": 500
    },
    {
      "epoch": 0.05194535348813049,
      "grad_norm": 4.882477760314941,
      "learning_rate": 1.8961092930237392e-05,
      "loss": 1.1416,
      "step": 1000
    },
    {
      "epoch": 0.07791803023219573,
      "grad_norm": 4.778675079345703,
      "learning_rate": 1.8441639395356087e-05,
      "loss": 0.9463,
      "step": 1500
    },
    {
      "epoch": 0.10389070697626097,
      "grad_norm": 3.6213603019714355,
      "learning_rate": 1.7922185860474782e-05,
      "loss": 0.8409,
      "step": 2000
    },
    {
      "epoch": 0.12986338372032621,
      "grad_norm": 3.8997128009796143,
      "learning_rate": 1.7402732325593478e-05,
      "loss": 0.776,
      "step": 2500
    },
    {
      "epoch": 0.15583606046439147,
      "grad_norm": 3.936784267425537,
      "learning_rate": 1.6883278790712173e-05,
      "loss": 0.7172,
      "step": 3000
    },
    {
      "epoch": 0.1818087372084567,
      "grad_norm": 4.620105743408203,
      "learning_rate": 1.6363825255830868e-05,
      "loss": 0.678,
      "step": 3500
    },
    {
      "epoch": 0.20778141395252195,
      "grad_norm": 3.3389108180999756,
      "learning_rate": 1.5844371720949563e-05,
      "loss": 0.6425,
      "step": 4000
    },
    {
      "epoch": 0.2337540906965872,
      "grad_norm": 3.794318675994873,
      "learning_rate": 1.5324918186068258e-05,
      "loss": 0.613,
      "step": 4500
    },
    {
      "epoch": 0.25972676744065243,
      "grad_norm": 3.75048565864563,
      "learning_rate": 1.4805464651186952e-05,
      "loss": 0.5985,
      "step": 5000
    },
    {
      "epoch": 0.28569944418471765,
      "grad_norm": 4.480340003967285,
      "learning_rate": 1.4286011116305647e-05,
      "loss": 0.5773,
      "step": 5500
    },
    {
      "epoch": 0.31167212092878294,
      "grad_norm": 3.5545272827148438,
      "learning_rate": 1.3766557581424342e-05,
      "loss": 0.5627,
      "step": 6000
    },
    {
      "epoch": 0.33764479767284816,
      "grad_norm": 4.083143711090088,
      "learning_rate": 1.3247104046543037e-05,
      "loss": 0.5313,
      "step": 6500
    },
    {
      "epoch": 0.3636174744169134,
      "grad_norm": 2.8664638996124268,
      "learning_rate": 1.2727650511661732e-05,
      "loss": 0.5296,
      "step": 7000
    },
    {
      "epoch": 0.38959015116097867,
      "grad_norm": 3.6368818283081055,
      "learning_rate": 1.220819697678043e-05,
      "loss": 0.5205,
      "step": 7500
    },
    {
      "epoch": 0.4155628279050439,
      "grad_norm": 3.749138116836548,
      "learning_rate": 1.1688743441899125e-05,
      "loss": 0.511,
      "step": 8000
    },
    {
      "epoch": 0.4415355046491091,
      "grad_norm": 4.568912029266357,
      "learning_rate": 1.1169289907017818e-05,
      "loss": 0.4949,
      "step": 8500
    },
    {
      "epoch": 0.4675081813931744,
      "grad_norm": 3.0868334770202637,
      "learning_rate": 1.0649836372136513e-05,
      "loss": 0.4912,
      "step": 9000
    },
    {
      "epoch": 0.49348085813723963,
      "grad_norm": 3.547401189804077,
      "learning_rate": 1.0130382837255208e-05,
      "loss": 0.4754,
      "step": 9500
    },
    {
      "epoch": 0.5194535348813049,
      "grad_norm": 2.4956228733062744,
      "learning_rate": 9.610929302373904e-06,
      "loss": 0.4761,
      "step": 10000
    },
    {
      "epoch": 0.5454262116253701,
      "grad_norm": 3.460627555847168,
      "learning_rate": 9.091475767492599e-06,
      "loss": 0.457,
      "step": 10500
    },
    {
      "epoch": 0.5713988883694353,
      "grad_norm": 4.2083740234375,
      "learning_rate": 8.572022232611294e-06,
      "loss": 0.4568,
      "step": 11000
    },
    {
      "epoch": 0.5973715651135006,
      "grad_norm": 3.801851511001587,
      "learning_rate": 8.052568697729989e-06,
      "loss": 0.4506,
      "step": 11500
    },
    {
      "epoch": 0.6233442418575659,
      "grad_norm": 3.7149624824523926,
      "learning_rate": 7.533115162848684e-06,
      "loss": 0.4403,
      "step": 12000
    },
    {
      "epoch": 0.6493169186016311,
      "grad_norm": 3.651339530944824,
      "learning_rate": 7.013661627967379e-06,
      "loss": 0.4366,
      "step": 12500
    },
    {
      "epoch": 0.6752895953456963,
      "grad_norm": 3.271475076675415,
      "learning_rate": 6.494208093086074e-06,
      "loss": 0.4328,
      "step": 13000
    },
    {
      "epoch": 0.7012622720897616,
      "grad_norm": 2.417835235595703,
      "learning_rate": 5.97475455820477e-06,
      "loss": 0.4265,
      "step": 13500
    },
    {
      "epoch": 0.7272349488338268,
      "grad_norm": 3.4311044216156006,
      "learning_rate": 5.455301023323464e-06,
      "loss": 0.4237,
      "step": 14000
    },
    {
      "epoch": 0.753207625577892,
      "grad_norm": 3.4447181224823,
      "learning_rate": 4.935847488442159e-06,
      "loss": 0.4221,
      "step": 14500
    },
    {
      "epoch": 0.7791803023219573,
      "grad_norm": 2.97375226020813,
      "learning_rate": 4.416393953560854e-06,
      "loss": 0.4101,
      "step": 15000
    },
    {
      "epoch": 0.8051529790660226,
      "grad_norm": 3.5221662521362305,
      "learning_rate": 3.89694041867955e-06,
      "loss": 0.4148,
      "step": 15500
    },
    {
      "epoch": 0.8311256558100878,
      "grad_norm": 2.455679178237915,
      "learning_rate": 3.3774868837982445e-06,
      "loss": 0.401,
      "step": 16000
    },
    {
      "epoch": 0.857098332554153,
      "grad_norm": 2.8382952213287354,
      "learning_rate": 2.8580333489169397e-06,
      "loss": 0.3988,
      "step": 16500
    },
    {
      "epoch": 0.8830710092982182,
      "grad_norm": 3.6632564067840576,
      "learning_rate": 2.338579814035635e-06,
      "loss": 0.4032,
      "step": 17000
    },
    {
      "epoch": 0.9090436860422835,
      "grad_norm": 3.332911968231201,
      "learning_rate": 1.8191262791543298e-06,
      "loss": 0.4008,
      "step": 17500
    },
    {
      "epoch": 0.9350163627863488,
      "grad_norm": 2.854703426361084,
      "learning_rate": 1.2996727442730248e-06,
      "loss": 0.4004,
      "step": 18000
    },
    {
      "epoch": 0.960989039530414,
      "grad_norm": 2.5069665908813477,
      "learning_rate": 7.802192093917199e-07,
      "loss": 0.3947,
      "step": 18500
    },
    {
      "epoch": 0.9869617162744793,
      "grad_norm": 2.937397003173828,
      "learning_rate": 2.6076567451041507e-07,
      "loss": 0.3916,
      "step": 19000
    }
  ],
  "logging_steps": 500,
  "max_steps": 19251,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.1363243784011776e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}