{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 48660,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "learning_rate": 2.6445129469790383e-05,
      "loss": 0.4806,
      "step": 1000
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.5890258939580763e-05,
      "loss": 0.2042,
      "step": 2000
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.5335388409371144e-05,
      "loss": 0.0906,
      "step": 3000
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.4780517879161528e-05,
      "loss": 0.075,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9802919017058749,
      "eval_f1": 0.8948306402542086,
      "eval_loss": 0.057683270424604416,
      "eval_precision": 0.8932146289317684,
      "eval_recall": 0.8964525095771946,
      "eval_runtime": 167.7197,
      "eval_samples_per_second": 232.102,
      "eval_steps_per_second": 7.256,
      "step": 4866
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.4225647348951912e-05,
      "loss": 0.0664,
      "step": 5000
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.3670776818742292e-05,
      "loss": 0.0585,
      "step": 6000
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.3115906288532676e-05,
      "loss": 0.0564,
      "step": 7000
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.2561035758323057e-05,
      "loss": 0.0549,
      "step": 8000
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.2006165228113437e-05,
      "loss": 0.0532,
      "step": 9000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9833089798732002,
      "eval_f1": 0.9123255599026524,
      "eval_loss": 0.048600517213344574,
      "eval_precision": 0.9153477632428206,
      "eval_recall": 0.9093232477030085,
      "eval_runtime": 162.2183,
      "eval_samples_per_second": 239.973,
      "eval_steps_per_second": 7.502,
      "step": 9732
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.145129469790382e-05,
      "loss": 0.0508,
      "step": 10000
    },
    {
      "epoch": 2.26,
      "learning_rate": 2.0896424167694205e-05,
      "loss": 0.0473,
      "step": 11000
    },
    {
      "epoch": 2.47,
      "learning_rate": 2.0341553637484585e-05,
      "loss": 0.0465,
      "step": 12000
    },
    {
      "epoch": 2.67,
      "learning_rate": 1.978668310727497e-05,
      "loss": 0.0453,
      "step": 13000
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.923181257706535e-05,
      "loss": 0.0445,
      "step": 14000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9861761750342243,
      "eval_f1": 0.9273251055750155,
      "eval_loss": 0.04213447496294975,
      "eval_precision": 0.9338007043530336,
      "eval_recall": 0.9209387005358894,
      "eval_runtime": 161.9782,
      "eval_samples_per_second": 240.329,
      "eval_steps_per_second": 7.513,
      "step": 14598
    },
    {
      "epoch": 3.08,
      "learning_rate": 1.8676942046855734e-05,
      "loss": 0.0416,
      "step": 15000
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.8122071516646114e-05,
      "loss": 0.039,
      "step": 16000
    },
    {
      "epoch": 3.49,
      "learning_rate": 1.7567200986436498e-05,
      "loss": 0.0383,
      "step": 17000
    },
    {
      "epoch": 3.7,
      "learning_rate": 1.7012330456226882e-05,
      "loss": 0.0371,
      "step": 18000
    },
    {
      "epoch": 3.9,
      "learning_rate": 1.645745992601726e-05,
      "loss": 0.0368,
      "step": 19000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.988197674042286,
      "eval_f1": 0.938523579208563,
      "eval_loss": 0.03771742060780525,
      "eval_precision": 0.9495865278134689,
      "eval_recall": 0.9277154349518386,
      "eval_runtime": 161.0315,
      "eval_samples_per_second": 241.741,
      "eval_steps_per_second": 7.558,
      "step": 19464
    },
    {
      "epoch": 4.11,
      "learning_rate": 1.5902589395807643e-05,
      "loss": 0.0338,
      "step": 20000
    },
    {
      "epoch": 4.32,
      "learning_rate": 1.5347718865598027e-05,
      "loss": 0.0318,
      "step": 21000
    },
    {
      "epoch": 4.52,
      "learning_rate": 1.479284833538841e-05,
      "loss": 0.0317,
      "step": 22000
    },
    {
      "epoch": 4.73,
      "learning_rate": 1.4237977805178791e-05,
      "loss": 0.0313,
      "step": 23000
    },
    {
      "epoch": 4.93,
      "learning_rate": 1.3683107274969172e-05,
      "loss": 0.0305,
      "step": 24000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9898844141091488,
      "eval_f1": 0.9479650837365973,
      "eval_loss": 0.034242045134305954,
      "eval_precision": 0.9554215497061004,
      "eval_recall": 0.9406241025613239,
      "eval_runtime": 161.8424,
      "eval_samples_per_second": 240.53,
      "eval_steps_per_second": 7.52,
      "step": 24330
    },
    {
      "epoch": 5.14,
      "learning_rate": 1.3128236744759554e-05,
      "loss": 0.0279,
      "step": 25000
    },
    {
      "epoch": 5.34,
      "learning_rate": 1.2573366214549938e-05,
      "loss": 0.0271,
      "step": 26000
    },
    {
      "epoch": 5.55,
      "learning_rate": 1.201849568434032e-05,
      "loss": 0.0265,
      "step": 27000
    },
    {
      "epoch": 5.75,
      "learning_rate": 1.1463625154130702e-05,
      "loss": 0.0265,
      "step": 28000
    },
    {
      "epoch": 5.96,
      "learning_rate": 1.0908754623921085e-05,
      "loss": 0.0258,
      "step": 29000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9903702696842303,
      "eval_f1": 0.9505588214114149,
      "eval_loss": 0.033819206058979034,
      "eval_precision": 0.9595477951054691,
      "eval_recall": 0.9417367007490169,
      "eval_runtime": 162.9235,
      "eval_samples_per_second": 238.934,
      "eval_steps_per_second": 7.47,
      "step": 29196
    },
    {
      "epoch": 6.17,
      "learning_rate": 1.0353884093711467e-05,
      "loss": 0.0237,
      "step": 30000
    },
    {
      "epoch": 6.37,
      "learning_rate": 9.799013563501849e-06,
      "loss": 0.0226,
      "step": 31000
    },
    {
      "epoch": 6.58,
      "learning_rate": 9.244143033292231e-06,
      "loss": 0.0224,
      "step": 32000
    },
    {
      "epoch": 6.78,
      "learning_rate": 8.689272503082614e-06,
      "loss": 0.0226,
      "step": 33000
    },
    {
      "epoch": 6.99,
      "learning_rate": 8.134401972872996e-06,
      "loss": 0.0218,
      "step": 34000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.991240440660084,
      "eval_f1": 0.9552142785098141,
      "eval_loss": 0.03187013044953346,
      "eval_precision": 0.9611628825560302,
      "eval_recall": 0.9493388529762905,
      "eval_runtime": 162.5283,
      "eval_samples_per_second": 239.515,
      "eval_steps_per_second": 7.488,
      "step": 34062
    },
    {
      "epoch": 7.19,
      "learning_rate": 7.579531442663379e-06,
      "loss": 0.0198,
      "step": 35000
    },
    {
      "epoch": 7.4,
      "learning_rate": 7.02466091245376e-06,
      "loss": 0.0194,
      "step": 36000
    },
    {
      "epoch": 7.6,
      "learning_rate": 6.469790382244143e-06,
      "loss": 0.0191,
      "step": 37000
    },
    {
      "epoch": 7.81,
      "learning_rate": 5.914919852034525e-06,
      "loss": 0.0195,
      "step": 38000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9916081698172439,
      "eval_f1": 0.9570525940763954,
      "eval_loss": 0.032054293900728226,
      "eval_precision": 0.9632173898726165,
      "eval_recall": 0.9509662084423806,
      "eval_runtime": 161.4483,
      "eval_samples_per_second": 241.117,
      "eval_steps_per_second": 7.538,
      "step": 38928
    },
    {
      "epoch": 8.01,
      "learning_rate": 5.360049321824907e-06,
      "loss": 0.0191,
      "step": 39000
    },
    {
      "epoch": 8.22,
      "learning_rate": 4.80517879161529e-06,
      "loss": 0.0169,
      "step": 40000
    },
    {
      "epoch": 8.43,
      "learning_rate": 4.250308261405672e-06,
      "loss": 0.0168,
      "step": 41000
    },
    {
      "epoch": 8.63,
      "learning_rate": 3.6954377311960542e-06,
      "loss": 0.0169,
      "step": 42000
    },
    {
      "epoch": 8.84,
      "learning_rate": 3.1405672009864364e-06,
      "loss": 0.0166,
      "step": 43000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9917976979912037,
      "eval_f1": 0.9580005448106782,
      "eval_loss": 0.03258174657821655,
      "eval_precision": 0.9632642552328989,
      "eval_recall": 0.9527940483221622,
      "eval_runtime": 163.1243,
      "eval_samples_per_second": 238.64,
      "eval_steps_per_second": 7.461,
      "step": 43794
    },
    {
      "epoch": 9.04,
      "learning_rate": 2.5856966707768186e-06,
      "loss": 0.017,
      "step": 44000
    },
    {
      "epoch": 9.25,
      "learning_rate": 2.030826140567201e-06,
      "loss": 0.0157,
      "step": 45000
    },
    {
      "epoch": 9.45,
      "learning_rate": 1.4759556103575833e-06,
      "loss": 0.0153,
      "step": 46000
    },
    {
      "epoch": 9.66,
      "learning_rate": 9.210850801479655e-07,
      "loss": 0.0151,
      "step": 47000
    },
    {
      "epoch": 9.86,
      "learning_rate": 3.662145499383477e-07,
      "loss": 0.015,
      "step": 48000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9919617399859543,
      "eval_f1": 0.9588266260051915,
      "eval_loss": 0.03259881213307381,
      "eval_precision": 0.963670430434156,
      "eval_recall": 0.9540312719562041,
      "eval_runtime": 167.3442,
      "eval_samples_per_second": 232.622,
      "eval_steps_per_second": 7.272,
      "step": 48660
    }
  ],
  "max_steps": 48660,
  "num_train_epochs": 10,
  "total_flos": 5.086523689353216e+16,
  "trial_name": null,
  "trial_params": null
}