{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 6252,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 2.6240322589874268,
      "learning_rate": 1.974664107485605e-05,
      "loss": 0.692889175415039,
      "step": 100
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 1.6500952243804932,
      "learning_rate": 1.9490722968650032e-05,
      "loss": 0.6690621948242188,
      "step": 200
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 5.539139747619629,
      "learning_rate": 1.923480486244402e-05,
      "loss": 0.6443107604980469,
      "step": 300
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 9.561639785766602,
      "learning_rate": 1.8978886756238006e-05,
      "loss": 0.6174827194213868,
      "step": 400
    },
    {
      "epoch": 0.3198976327575176,
      "grad_norm": 3.9405109882354736,
      "learning_rate": 1.8722968650031992e-05,
      "loss": 0.603485221862793,
      "step": 500
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 5.654637336730957,
      "learning_rate": 1.846705054382598e-05,
      "loss": 0.5690624237060546,
      "step": 600
    },
    {
      "epoch": 0.44785668586052463,
      "grad_norm": 6.288730144500732,
      "learning_rate": 1.8211132437619962e-05,
      "loss": 0.5585448455810547,
      "step": 700
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 7.303677558898926,
      "learning_rate": 1.795521433141395e-05,
      "loss": 0.5453743362426757,
      "step": 800
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 4.167948246002197,
      "learning_rate": 1.7699296225207935e-05,
      "loss": 0.5284878540039063,
      "step": 900
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 6.335079669952393,
      "learning_rate": 1.744337811900192e-05,
      "loss": 0.497203369140625,
      "step": 1000
    },
    {
      "epoch": 0.7037747920665387,
      "grad_norm": 9.398835182189941,
      "learning_rate": 1.7187460012795908e-05,
      "loss": 0.4662479782104492,
      "step": 1100
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 17.086259841918945,
      "learning_rate": 1.693154190658989e-05,
      "loss": 0.4858377456665039,
      "step": 1200
    },
    {
      "epoch": 0.8317338451695457,
      "grad_norm": 11.53818416595459,
      "learning_rate": 1.6675623800383878e-05,
      "loss": 0.45729072570800783,
      "step": 1300
    },
    {
      "epoch": 0.8957133717210493,
      "grad_norm": 22.93279457092285,
      "learning_rate": 1.6419705694177864e-05,
      "loss": 0.45677249908447265,
      "step": 1400
    },
    {
      "epoch": 0.9596928982725528,
      "grad_norm": 15.763897895812988,
      "learning_rate": 1.616378758797185e-05,
      "loss": 0.4614885711669922,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.81124,
      "eval_f1": 0.8026596411993476,
      "eval_loss": 0.4272981286048889,
      "eval_precision": 0.8408832033645842,
      "eval_recall": 0.76776,
      "eval_runtime": 16.5749,
      "eval_samples_per_second": 1508.308,
      "eval_steps_per_second": 94.299,
      "step": 1563
    },
    {
      "epoch": 1.0236724248240563,
      "grad_norm": 16.664216995239258,
      "learning_rate": 1.5907869481765838e-05,
      "loss": 0.44625389099121093,
      "step": 1600
    },
    {
      "epoch": 1.0876519513755598,
      "grad_norm": 23.07805824279785,
      "learning_rate": 1.565195137555982e-05,
      "loss": 0.44664024353027343,
      "step": 1700
    },
    {
      "epoch": 1.1516314779270633,
      "grad_norm": 8.32645320892334,
      "learning_rate": 1.5396033269353807e-05,
      "loss": 0.42939315795898436,
      "step": 1800
    },
    {
      "epoch": 1.2156110044785668,
      "grad_norm": 7.903297424316406,
      "learning_rate": 1.5140115163147796e-05,
      "loss": 0.41601951599121095,
      "step": 1900
    },
    {
      "epoch": 1.2795905310300704,
      "grad_norm": 11.639277458190918,
      "learning_rate": 1.488419705694178e-05,
      "loss": 0.39629173278808594,
      "step": 2000
    },
    {
      "epoch": 1.3435700575815739,
      "grad_norm": 6.199832916259766,
      "learning_rate": 1.4628278950735765e-05,
      "loss": 0.3827814102172852,
      "step": 2100
    },
    {
      "epoch": 1.4075495841330774,
      "grad_norm": 17.21854019165039,
      "learning_rate": 1.4372360844529752e-05,
      "loss": 0.41142051696777343,
      "step": 2200
    },
    {
      "epoch": 1.471529110684581,
      "grad_norm": 15.716930389404297,
      "learning_rate": 1.4116442738323737e-05,
      "loss": 0.38613304138183596,
      "step": 2300
    },
    {
      "epoch": 1.5355086372360844,
      "grad_norm": 6.01155948638916,
      "learning_rate": 1.3860524632117725e-05,
      "loss": 0.41208648681640625,
      "step": 2400
    },
    {
      "epoch": 1.599488163787588,
      "grad_norm": 20.55832862854004,
      "learning_rate": 1.360460652591171e-05,
      "loss": 0.38446582794189454,
      "step": 2500
    },
    {
      "epoch": 1.6634676903390915,
      "grad_norm": 11.465950012207031,
      "learning_rate": 1.3348688419705695e-05,
      "loss": 0.37646575927734377,
      "step": 2600
    },
    {
      "epoch": 1.727447216890595,
      "grad_norm": 3.505220651626587,
      "learning_rate": 1.3092770313499681e-05,
      "loss": 0.3866144561767578,
      "step": 2700
    },
    {
      "epoch": 1.7914267434420985,
      "grad_norm": 27.13107681274414,
      "learning_rate": 1.2836852207293666e-05,
      "loss": 0.4025085830688477,
      "step": 2800
    },
    {
      "epoch": 1.855406269993602,
      "grad_norm": 7.345473766326904,
      "learning_rate": 1.2580934101087654e-05,
      "loss": 0.3890159225463867,
      "step": 2900
    },
    {
      "epoch": 1.9193857965451055,
      "grad_norm": 24.46322250366211,
      "learning_rate": 1.232501599488164e-05,
      "loss": 0.381514778137207,
      "step": 3000
    },
    {
      "epoch": 1.983365323096609,
      "grad_norm": 6.782553195953369,
      "learning_rate": 1.2069097888675624e-05,
      "loss": 0.3956758499145508,
      "step": 3100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8286,
      "eval_f1": 0.8181779607077694,
      "eval_loss": 0.3925381898880005,
      "eval_precision": 0.8711484593837535,
      "eval_recall": 0.77128,
      "eval_runtime": 18.1817,
      "eval_samples_per_second": 1375.01,
      "eval_steps_per_second": 85.966,
      "step": 3126
    },
    {
      "epoch": 2.0473448496481126,
      "grad_norm": 11.411704063415527,
      "learning_rate": 1.181317978246961e-05,
      "loss": 0.36985355377197265,
      "step": 3200
    },
    {
      "epoch": 2.111324376199616,
      "grad_norm": 8.180529594421387,
      "learning_rate": 1.1557261676263596e-05,
      "loss": 0.34660816192626953,
      "step": 3300
    },
    {
      "epoch": 2.1753039027511196,
      "grad_norm": 14.788076400756836,
      "learning_rate": 1.1301343570057584e-05,
      "loss": 0.3805205154418945,
      "step": 3400
    },
    {
      "epoch": 2.239283429302623,
      "grad_norm": 38.90132522583008,
      "learning_rate": 1.1045425463851569e-05,
      "loss": 0.36612781524658206,
      "step": 3500
    },
    {
      "epoch": 2.3032629558541267,
      "grad_norm": 6.464240550994873,
      "learning_rate": 1.0789507357645555e-05,
      "loss": 0.3882516098022461,
      "step": 3600
    },
    {
      "epoch": 2.36724248240563,
      "grad_norm": 12.745105743408203,
      "learning_rate": 1.053358925143954e-05,
      "loss": 0.37442840576171876,
      "step": 3700
    },
    {
      "epoch": 2.4312220089571337,
      "grad_norm": 18.671857833862305,
      "learning_rate": 1.0277671145233525e-05,
      "loss": 0.3458353424072266,
      "step": 3800
    },
    {
      "epoch": 2.495201535508637,
      "grad_norm": 14.760592460632324,
      "learning_rate": 1.0021753039027513e-05,
      "loss": 0.3635056686401367,
      "step": 3900
    },
    {
      "epoch": 2.5591810620601407,
      "grad_norm": 3.513972282409668,
      "learning_rate": 9.765834932821498e-06,
      "loss": 0.33845436096191406,
      "step": 4000
    },
    {
      "epoch": 2.6231605886116443,
      "grad_norm": 7.455184459686279,
      "learning_rate": 9.509916826615485e-06,
      "loss": 0.36538402557373045,
      "step": 4100
    },
    {
      "epoch": 2.6871401151631478,
      "grad_norm": 35.58430862426758,
      "learning_rate": 9.25399872040947e-06,
      "loss": 0.38003883361816404,
      "step": 4200
    },
    {
      "epoch": 2.7511196417146513,
      "grad_norm": 28.353757858276367,
      "learning_rate": 8.998080614203456e-06,
      "loss": 0.334156379699707,
      "step": 4300
    },
    {
      "epoch": 2.815099168266155,
      "grad_norm": 10.301733016967773,
      "learning_rate": 8.742162507997441e-06,
      "loss": 0.36084671020507814,
      "step": 4400
    },
    {
      "epoch": 2.8790786948176583,
      "grad_norm": 8.111748695373535,
      "learning_rate": 8.486244401791428e-06,
      "loss": 0.3733618545532227,
      "step": 4500
    },
    {
      "epoch": 2.943058221369162,
      "grad_norm": 7.716980934143066,
      "learning_rate": 8.230326295585414e-06,
      "loss": 0.37022560119628906,
      "step": 4600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8426,
      "eval_f1": 0.8457286235151135,
      "eval_loss": 0.36446496844291687,
      "eval_precision": 0.8292457907280695,
      "eval_recall": 0.86288,
      "eval_runtime": 13.8616,
      "eval_samples_per_second": 1803.544,
      "eval_steps_per_second": 112.758,
      "step": 4689
    },
    {
      "epoch": 3.0070377479206654,
      "grad_norm": 8.766412734985352,
      "learning_rate": 7.974408189379399e-06,
      "loss": 0.3578424835205078,
      "step": 4700
    },
    {
      "epoch": 3.071017274472169,
      "grad_norm": 25.10895538330078,
      "learning_rate": 7.718490083173386e-06,
      "loss": 0.36146461486816406,
      "step": 4800
    },
    {
      "epoch": 3.1349968010236724,
      "grad_norm": 2.3490066528320312,
      "learning_rate": 7.462571976967371e-06,
      "loss": 0.33738922119140624,
      "step": 4900
    },
    {
      "epoch": 3.198976327575176,
      "grad_norm": 13.975132942199707,
      "learning_rate": 7.206653870761356e-06,
      "loss": 0.326907958984375,
      "step": 5000
    },
    {
      "epoch": 3.2629558541266794,
      "grad_norm": 6.52653694152832,
      "learning_rate": 6.950735764555343e-06,
      "loss": 0.34798374176025393,
      "step": 5100
    },
    {
      "epoch": 3.326935380678183,
      "grad_norm": 5.691891670227051,
      "learning_rate": 6.694817658349328e-06,
      "loss": 0.36636493682861326,
      "step": 5200
    },
    {
      "epoch": 3.3909149072296865,
      "grad_norm": 25.656173706054688,
      "learning_rate": 6.438899552143315e-06,
      "loss": 0.3263176727294922,
      "step": 5300
    },
    {
      "epoch": 3.45489443378119,
      "grad_norm": 10.740619659423828,
      "learning_rate": 6.182981445937301e-06,
      "loss": 0.36173702239990235,
      "step": 5400
    },
    {
      "epoch": 3.5188739603326935,
      "grad_norm": 6.179443836212158,
      "learning_rate": 5.927063339731286e-06,
      "loss": 0.3383364486694336,
      "step": 5500
    },
    {
      "epoch": 3.582853486884197,
      "grad_norm": 8.635146141052246,
      "learning_rate": 5.671145233525273e-06,
      "loss": 0.3060850715637207,
      "step": 5600
    },
    {
      "epoch": 3.6468330134357005,
      "grad_norm": 12.844294548034668,
      "learning_rate": 5.415227127319258e-06,
      "loss": 0.3492905807495117,
      "step": 5700
    },
    {
      "epoch": 3.710812539987204,
      "grad_norm": 3.7722866535186768,
      "learning_rate": 5.159309021113244e-06,
      "loss": 0.352115592956543,
      "step": 5800
    },
    {
      "epoch": 3.7747920665387076,
      "grad_norm": 16.642221450805664,
      "learning_rate": 4.90339091490723e-06,
      "loss": 0.3466293716430664,
      "step": 5900
    },
    {
      "epoch": 3.838771593090211,
      "grad_norm": 22.054513931274414,
      "learning_rate": 4.647472808701216e-06,
      "loss": 0.3272230529785156,
      "step": 6000
    },
    {
      "epoch": 3.9027511196417146,
      "grad_norm": 5.188161849975586,
      "learning_rate": 4.391554702495202e-06,
      "loss": 0.3530220794677734,
      "step": 6100
    },
    {
      "epoch": 3.966730646193218,
      "grad_norm": 24.137426376342773,
      "learning_rate": 4.135636596289187e-06,
      "loss": 0.3384724807739258,
      "step": 6200
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8466,
      "eval_f1": 0.845081801656231,
      "eval_loss": 0.36203694343566895,
      "eval_precision": 0.8535291717666259,
      "eval_recall": 0.8368,
      "eval_runtime": 16.3968,
      "eval_samples_per_second": 1524.69,
      "eval_steps_per_second": 95.324,
      "step": 6252
    }
  ],
  "logging_steps": 100,
  "max_steps": 7815,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 63524352000000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}