{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.174858634188778,
  "eval_steps": 1000,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04349717268377556,
      "grad_norm": 1.1873760223388672,
      "learning_rate": 2.8695652173913046e-06,
      "loss": 0.017874032258987427,
      "step": 100
    },
    {
      "epoch": 0.08699434536755112,
      "grad_norm": 0.42400866746902466,
      "learning_rate": 5.768115942028986e-06,
      "loss": 0.019751017093658448,
      "step": 200
    },
    {
      "epoch": 0.13049151805132667,
      "grad_norm": 0.4099847972393036,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.014439672231674194,
      "step": 300
    },
    {
      "epoch": 0.17398869073510223,
      "grad_norm": 0.4237093925476074,
      "learning_rate": 9.917582417582419e-06,
      "loss": 0.019586087465286256,
      "step": 400
    },
    {
      "epoch": 0.21748586341887777,
      "grad_norm": 0.5307211875915527,
      "learning_rate": 9.764957264957265e-06,
      "loss": 0.02108067512512207,
      "step": 500
    },
    {
      "epoch": 0.26098303610265333,
      "grad_norm": 0.2467508465051651,
      "learning_rate": 9.612332112332114e-06,
      "loss": 0.017134275436401367,
      "step": 600
    },
    {
      "epoch": 0.3044802087864289,
      "grad_norm": 0.04444492980837822,
      "learning_rate": 9.45970695970696e-06,
      "loss": 0.014518336057662964,
      "step": 700
    },
    {
      "epoch": 0.34797738147020446,
      "grad_norm": 0.02670428715646267,
      "learning_rate": 9.307081807081807e-06,
      "loss": 0.015038586854934692,
      "step": 800
    },
    {
      "epoch": 0.39147455415397997,
      "grad_norm": 0.11947870254516602,
      "learning_rate": 9.154456654456656e-06,
      "loss": 0.01791533350944519,
      "step": 900
    },
    {
      "epoch": 0.43497172683775553,
      "grad_norm": 0.03927593678236008,
      "learning_rate": 9.001831501831502e-06,
      "loss": 0.012947161197662354,
      "step": 1000
    },
    {
      "epoch": 0.43497172683775553,
      "eval_accuracy": 0.9987446666666666,
      "eval_f1": 0.9987346048644515,
      "eval_loss": 0.01923435740172863,
      "eval_precision": 0.998726833632803,
      "eval_recall": 0.9987446666666666,
      "eval_runtime": 29.2875,
      "eval_samples_per_second": 170.721,
      "eval_steps_per_second": 21.34,
      "step": 1000
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 0.4049844443798065,
      "learning_rate": 8.849206349206349e-06,
      "loss": 0.02207942247390747,
      "step": 1100
    },
    {
      "epoch": 0.5219660722053067,
      "grad_norm": 0.08053509891033173,
      "learning_rate": 8.696581196581197e-06,
      "loss": 0.01587142825126648,
      "step": 1200
    },
    {
      "epoch": 0.5654632448890822,
      "grad_norm": 1.8759474754333496,
      "learning_rate": 8.543956043956044e-06,
      "loss": 0.014381803274154663,
      "step": 1300
    },
    {
      "epoch": 0.6089604175728578,
      "grad_norm": 1.6190632581710815,
      "learning_rate": 8.391330891330893e-06,
      "loss": 0.015616736412048339,
      "step": 1400
    },
    {
      "epoch": 0.6524575902566333,
      "grad_norm": 0.2359640896320343,
      "learning_rate": 8.23870573870574e-06,
      "loss": 0.01666579842567444,
      "step": 1500
    },
    {
      "epoch": 0.6959547629404089,
      "grad_norm": 0.4448085129261017,
      "learning_rate": 8.086080586080588e-06,
      "loss": 0.018115322589874267,
      "step": 1600
    },
    {
      "epoch": 0.7394519356241844,
      "grad_norm": 0.6740186214447021,
      "learning_rate": 7.933455433455434e-06,
      "loss": 0.014048123359680175,
      "step": 1700
    },
    {
      "epoch": 0.7829491083079599,
      "grad_norm": 0.03318515792489052,
      "learning_rate": 7.780830280830281e-06,
      "loss": 0.015549888610839844,
      "step": 1800
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 0.2157498300075531,
      "learning_rate": 7.6282051282051286e-06,
      "loss": 0.014837932586669923,
      "step": 1900
    },
    {
      "epoch": 0.8699434536755111,
      "grad_norm": 0.16669438779354095,
      "learning_rate": 7.475579975579976e-06,
      "loss": 0.015988308191299438,
      "step": 2000
    },
    {
      "epoch": 0.8699434536755111,
      "eval_accuracy": 0.998754,
      "eval_f1": 0.9987447764128639,
      "eval_loss": 0.018810242414474487,
      "eval_precision": 0.9987375090137124,
      "eval_recall": 0.998754,
      "eval_runtime": 29.3171,
      "eval_samples_per_second": 170.549,
      "eval_steps_per_second": 21.319,
      "step": 2000
    },
    {
      "epoch": 0.9134406263592867,
      "grad_norm": 0.1879555583000183,
      "learning_rate": 7.322954822954823e-06,
      "loss": 0.014088320732116699,
      "step": 2100
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 0.09590628743171692,
      "learning_rate": 7.170329670329671e-06,
      "loss": 0.01723169445991516,
      "step": 2200
    },
    {
      "epoch": 1.0004349717268377,
      "grad_norm": 0.1197345182299614,
      "learning_rate": 7.017704517704518e-06,
      "loss": 0.019008680582046508,
      "step": 2300
    },
    {
      "epoch": 1.0439321444106133,
      "grad_norm": 0.2402680516242981,
      "learning_rate": 6.8650793650793654e-06,
      "loss": 0.012565597295761108,
      "step": 2400
    },
    {
      "epoch": 1.087429317094389,
      "grad_norm": 0.030996643006801605,
      "learning_rate": 6.712454212454212e-06,
      "loss": 0.010086134672164918,
      "step": 2500
    },
    {
      "epoch": 1.1309264897781643,
      "grad_norm": 3.238438844680786,
      "learning_rate": 6.5598290598290605e-06,
      "loss": 0.016254127025604248,
      "step": 2600
    },
    {
      "epoch": 1.17442366246194,
      "grad_norm": 0.028059102594852448,
      "learning_rate": 6.407203907203908e-06,
      "loss": 0.013029559850692748,
      "step": 2700
    },
    {
      "epoch": 1.2179208351457156,
      "grad_norm": 0.06354221701622009,
      "learning_rate": 6.254578754578755e-06,
      "loss": 0.015041029453277588,
      "step": 2800
    },
    {
      "epoch": 1.2614180078294912,
      "grad_norm": 0.0685008093714714,
      "learning_rate": 6.101953601953603e-06,
      "loss": 0.012073255777359009,
      "step": 2900
    },
    {
      "epoch": 1.3049151805132666,
      "grad_norm": 0.0475081130862236,
      "learning_rate": 5.94932844932845e-06,
      "loss": 0.014265480041503907,
      "step": 3000
    },
    {
      "epoch": 1.3049151805132666,
      "eval_accuracy": 0.998752,
      "eval_f1": 0.998738876760062,
      "eval_loss": 0.02136029303073883,
      "eval_precision": 0.9987296967935673,
      "eval_recall": 0.998752,
      "eval_runtime": 29.2941,
      "eval_samples_per_second": 170.683,
      "eval_steps_per_second": 21.335,
      "step": 3000
    },
    {
      "epoch": 1.3484123531970422,
      "grad_norm": 0.3057118356227875,
      "learning_rate": 5.796703296703297e-06,
      "loss": 0.012346909046173096,
      "step": 3100
    },
    {
      "epoch": 1.3919095258808176,
      "grad_norm": 0.014957386068999767,
      "learning_rate": 5.644078144078144e-06,
      "loss": 0.011055607795715332,
      "step": 3200
    },
    {
      "epoch": 1.4354066985645932,
      "grad_norm": 0.32580187916755676,
      "learning_rate": 5.4914529914529925e-06,
      "loss": 0.010661197900772095,
      "step": 3300
    },
    {
      "epoch": 1.4789038712483689,
      "grad_norm": 0.633515477180481,
      "learning_rate": 5.338827838827839e-06,
      "loss": 0.013761337995529175,
      "step": 3400
    },
    {
      "epoch": 1.5224010439321445,
      "grad_norm": 0.1888076215982437,
      "learning_rate": 5.186202686202687e-06,
      "loss": 0.011319246292114258,
      "step": 3500
    },
    {
      "epoch": 1.56589821661592,
      "grad_norm": 0.11967664957046509,
      "learning_rate": 5.033577533577534e-06,
      "loss": 0.010699814558029175,
      "step": 3600
    },
    {
      "epoch": 1.6093953892996955,
      "grad_norm": 1.1530064344406128,
      "learning_rate": 4.880952380952381e-06,
      "loss": 0.011285524368286132,
      "step": 3700
    },
    {
      "epoch": 1.6528925619834711,
      "grad_norm": 0.23583859205245972,
      "learning_rate": 4.7283272283272285e-06,
      "loss": 0.012795346975326537,
      "step": 3800
    },
    {
      "epoch": 1.6963897346672465,
      "grad_norm": 1.0408198833465576,
      "learning_rate": 4.575702075702076e-06,
      "loss": 0.012792168855667115,
      "step": 3900
    },
    {
      "epoch": 1.7398869073510221,
      "grad_norm": 0.09672334045171738,
      "learning_rate": 4.423076923076924e-06,
      "loss": 0.010303473472595215,
      "step": 4000
    },
    {
      "epoch": 1.7398869073510221,
      "eval_accuracy": 0.9987613333333333,
      "eval_f1": 0.9987487342857478,
      "eval_loss": 0.021380659192800522,
      "eval_precision": 0.998739829053503,
      "eval_recall": 0.9987613333333333,
      "eval_runtime": 29.2518,
      "eval_samples_per_second": 170.929,
      "eval_steps_per_second": 21.366,
      "step": 4000
    },
    {
      "epoch": 1.7833840800347978,
      "grad_norm": 0.19785387814044952,
      "learning_rate": 4.27045177045177e-06,
      "loss": 0.013082098960876466,
      "step": 4100
    },
    {
      "epoch": 1.8268812527185734,
      "grad_norm": 0.022854823619127274,
      "learning_rate": 4.117826617826618e-06,
      "loss": 0.011326223611831665,
      "step": 4200
    },
    {
      "epoch": 1.870378425402349,
      "grad_norm": 0.39354178309440613,
      "learning_rate": 3.965201465201465e-06,
      "loss": 0.011685781478881836,
      "step": 4300
    },
    {
      "epoch": 1.9138755980861244,
      "grad_norm": 0.5049183368682861,
      "learning_rate": 3.8125763125763125e-06,
      "loss": 0.013935636281967163,
      "step": 4400
    },
    {
      "epoch": 1.9573727707698998,
      "grad_norm": 0.31575822830200195,
      "learning_rate": 3.65995115995116e-06,
      "loss": 0.01821691632270813,
      "step": 4500
    },
    {
      "epoch": 2.0008699434536754,
      "grad_norm": 0.03354845568537712,
      "learning_rate": 3.507326007326007e-06,
      "loss": 0.01202067494392395,
      "step": 4600
    },
    {
      "epoch": 2.044367116137451,
      "grad_norm": 0.17201851308345795,
      "learning_rate": 3.3547008547008547e-06,
      "loss": 0.007187445163726807,
      "step": 4700
    },
    {
      "epoch": 2.0878642888212267,
      "grad_norm": 1.2300870418548584,
      "learning_rate": 3.2020757020757023e-06,
      "loss": 0.013125517368316651,
      "step": 4800
    },
    {
      "epoch": 2.1313614615050023,
      "grad_norm": 2.114861488342285,
      "learning_rate": 3.04945054945055e-06,
      "loss": 0.013083455562591552,
      "step": 4900
    },
    {
      "epoch": 2.174858634188778,
      "grad_norm": 0.17883101105690002,
      "learning_rate": 2.8968253968253974e-06,
      "loss": 0.010745112895965575,
      "step": 5000
    },
    {
      "epoch": 2.174858634188778,
      "eval_accuracy": 0.9987673333333333,
      "eval_f1": 0.998753649229471,
      "eval_loss": 0.022213751450181007,
      "eval_precision": 0.9987443671820871,
      "eval_recall": 0.9987673333333333,
      "eval_runtime": 29.3818,
      "eval_samples_per_second": 170.173,
      "eval_steps_per_second": 21.272,
      "step": 5000
    }
  ],
  "logging_steps": 100,
  "max_steps": 6897,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.358942107089254e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}