{
  "best_global_step": null,
  "best_metric": 0.9054671281010055,
  "best_model_checkpoint": null,
  "epoch": 1.1578947368421053,
  "eval_steps": 16,
  "global_step": 88,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 291.3879089355469,
      "learning_rate": 5e-06,
      "loss": 4.5409,
      "step": 4
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 203.68991088867188,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 3.7189,
      "step": 8
    },
    {
      "epoch": 0.10526315789473684,
      "eval_F1_err_corr": 0.6871469086338724,
      "eval_accuracy": 0.7513151602104257,
      "eval_correct_accuracy": 0.9983222883986244,
      "eval_error_accuracy": 0.523860477930856,
      "eval_f1": 0.0057361376673040155,
      "eval_loss": 1.093567132949829,
      "eval_pr_auc": 0.3045333732522034,
      "eval_precision": 0.3,
      "eval_recall": 0.0028957528957528956,
      "eval_runtime": 7.2032,
      "eval_samples_per_second": 162.011,
      "eval_steps_per_second": 1.388,
      "step": 8
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 187.05014038085938,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 4.2318,
      "step": 12
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 146.46641540527344,
      "learning_rate": 1.99967206113942e-05,
      "loss": 2.7212,
      "step": 16
    },
    {
      "epoch": 0.21052631578947367,
      "eval_F1_err_corr": 0.6332040138458732,
      "eval_accuracy": 0.6743185078909613,
      "eval_correct_accuracy": 0.5579058876929509,
      "eval_error_accuracy": 0.7319986862791484,
      "eval_f1": 0.5659655831739961,
      "eval_loss": 0.7970147132873535,
      "eval_pr_auc": 0.5909991957581218,
      "eval_precision": 0.4224548049476689,
      "eval_recall": 0.8571428571428571,
      "eval_runtime": 7.138,
      "eval_samples_per_second": 163.491,
      "eval_steps_per_second": 1.401,
      "step": 16
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 28.303598403930664,
      "learning_rate": 1.9982149887948264e-05,
      "loss": 2.6877,
      "step": 20
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 63.692806243896484,
      "learning_rate": 1.995594042425798e-05,
      "loss": 1.8805,
      "step": 24
    },
    {
      "epoch": 0.3157894736842105,
      "eval_F1_err_corr": 0.8195852671712573,
      "eval_accuracy": 0.8283118125298901,
      "eval_correct_accuracy": 0.9559562730173418,
      "eval_error_accuracy": 0.7172645896385392,
      "eval_f1": 0.5815850815850816,
      "eval_loss": 0.39416325092315674,
      "eval_pr_auc": 0.693011369968824,
      "eval_precision": 0.7338235294117647,
      "eval_recall": 0.48166023166023164,
      "eval_runtime": 7.1406,
      "eval_samples_per_second": 163.433,
      "eval_steps_per_second": 1.4,
      "step": 24
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 53.82140350341797,
      "learning_rate": 1.99181227793856e-05,
      "loss": 1.6956,
      "step": 28
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 38.888492584228516,
      "learning_rate": 1.9868741047013382e-05,
      "loss": 1.5156,
      "step": 32
    },
    {
      "epoch": 0.42105263157894735,
      "eval_F1_err_corr": 0.8118976385967145,
      "eval_accuracy": 0.8354854136776662,
      "eval_correct_accuracy": 0.9372372100616376,
      "eval_error_accuracy": 0.71612771037666,
      "eval_f1": 0.5651074589127687,
      "eval_loss": 0.36986085772514343,
      "eval_pr_auc": 0.7616394776557907,
      "eval_precision": 0.8186813186813187,
      "eval_recall": 0.4314671814671815,
      "eval_runtime": 7.1716,
      "eval_samples_per_second": 162.725,
      "eval_steps_per_second": 1.394,
      "step": 32
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 22.607288360595703,
      "learning_rate": 1.9807852804032306e-05,
      "loss": 1.4892,
      "step": 36
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 13.400656700134277,
      "learning_rate": 1.9735529043410012e-05,
      "loss": 1.2424,
      "step": 40
    },
    {
      "epoch": 0.5263157894736842,
      "eval_F1_err_corr": 0.8711215240506508,
      "eval_accuracy": 0.8627450980392157,
      "eval_correct_accuracy": 0.9620440825784337,
      "eval_error_accuracy": 0.7959010995250491,
      "eval_f1": 0.6835722160970231,
      "eval_loss": 0.3136674463748932,
      "eval_pr_auc": 0.7987692721100079,
      "eval_precision": 0.7969151670951157,
      "eval_recall": 0.5984555984555985,
      "eval_runtime": 7.1521,
      "eval_samples_per_second": 163.17,
      "eval_steps_per_second": 1.398,
      "step": 40
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 16.472789764404297,
      "learning_rate": 1.9651854091416175e-05,
      "loss": 1.2995,
      "step": 44
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 7.745436668395996,
      "learning_rate": 1.9556925509301844e-05,
      "loss": 1.1904,
      "step": 48
    },
    {
      "epoch": 0.631578947368421,
      "eval_F1_err_corr": 0.8839638940186375,
      "eval_accuracy": 0.8842659014825442,
      "eval_correct_accuracy": 0.9484455013462648,
      "eval_error_accuracy": 0.8276919152969574,
      "eval_f1": 0.7520491803278688,
      "eval_loss": 0.2730002999305725,
      "eval_pr_auc": 0.8327722297335601,
      "eval_precision": 0.8013100436681223,
      "eval_recall": 0.7084942084942085,
      "eval_runtime": 7.1492,
      "eval_samples_per_second": 163.234,
      "eval_steps_per_second": 1.399,
      "step": 48
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 22.183454513549805,
      "learning_rate": 1.9450853979547384e-05,
      "loss": 1.0703,
      "step": 52
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 10.418429374694824,
      "learning_rate": 1.9333763176811663e-05,
      "loss": 1.1166,
      "step": 56
    },
    {
      "epoch": 0.7368421052631579,
      "eval_F1_err_corr": 0.8963518458095878,
      "eval_accuracy": 0.8854615016738403,
      "eval_correct_accuracy": 0.9502566249131135,
      "eval_error_accuracy": 0.8482344335548118,
      "eval_f1": 0.7603801900950475,
      "eval_loss": 0.26140278577804565,
      "eval_pr_auc": 0.8394726873391715,
      "eval_precision": 0.7892004153686397,
      "eval_recall": 0.7335907335907336,
      "eval_runtime": 7.1393,
      "eval_samples_per_second": 163.461,
      "eval_steps_per_second": 1.401,
      "step": 56
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 24.996362686157227,
      "learning_rate": 1.9205789623732923e-05,
      "loss": 1.107,
      "step": 60
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 10.622379302978516,
      "learning_rate": 1.9067082531749496e-05,
      "loss": 1.0344,
      "step": 64
    },
    {
      "epoch": 0.8421052631578947,
      "eval_F1_err_corr": 0.8971597384167123,
      "eval_accuracy": 0.8928742228598756,
      "eval_correct_accuracy": 0.9511252134916257,
      "eval_error_accuracy": 0.8489893075764926,
      "eval_f1": 0.7764471057884231,
      "eval_loss": 0.25267964601516724,
      "eval_pr_auc": 0.8508672146171146,
      "eval_precision": 0.8037190082644629,
      "eval_recall": 0.750965250965251,
      "eval_runtime": 7.1659,
      "eval_samples_per_second": 162.854,
      "eval_steps_per_second": 1.395,
      "step": 64
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 4.826870441436768,
      "learning_rate": 1.891780362712594e-05,
      "loss": 0.984,
      "step": 68
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 8.766145706176758,
      "learning_rate": 1.875812696238745e-05,
      "loss": 0.9791,
      "step": 72
    },
    {
      "epoch": 0.9473684210526315,
      "eval_F1_err_corr": 0.89776260256973,
      "eval_accuracy": 0.8940698230511717,
      "eval_correct_accuracy": 0.9191008849787475,
      "eval_error_accuracy": 0.8773926386058739,
      "eval_f1": 0.7932804479701353,
      "eval_loss": 0.25162529945373535,
      "eval_pr_auc": 0.8580493064471059,
      "eval_precision": 0.7678410117434508,
      "eval_recall": 0.8204633204633205,
      "eval_runtime": 7.1451,
      "eval_samples_per_second": 163.329,
      "eval_steps_per_second": 1.4,
      "step": 72
    },
    {
      "epoch": 1.0,
      "grad_norm": 15.486649513244629,
      "learning_rate": 1.85882387133824e-05,
      "loss": 1.0899,
      "step": 76
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 9.650471687316895,
      "learning_rate": 1.840833696220963e-05,
      "loss": 0.61,
      "step": 80
    },
    {
      "epoch": 1.0526315789473684,
      "eval_F1_err_corr": 0.8951485557028362,
      "eval_accuracy": 0.8904830224772836,
      "eval_correct_accuracy": 0.9052260320962611,
      "eval_error_accuracy": 0.8852929850041195,
      "eval_f1": 0.7973451327433628,
      "eval_loss": 0.2587549686431885,
      "eval_pr_auc": 0.8644362216080673,
      "eval_precision": 0.7361111111111112,
      "eval_recall": 0.8696911196911197,
      "eval_runtime": 7.1493,
      "eval_samples_per_second": 163.233,
      "eval_steps_per_second": 1.399,
      "step": 80
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 7.722207546234131,
      "learning_rate": 1.8218631466263584e-05,
      "loss": 0.6206,
      "step": 84
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 23.517024993896484,
      "learning_rate": 1.801934341366655e-05,
      "loss": 0.6597,
      "step": 88
    },
    {
      "epoch": 1.1578947368421053,
      "eval_F1_err_corr": 0.9054671281010055,
      "eval_accuracy": 0.9033955045432808,
      "eval_correct_accuracy": 0.9527881095438347,
      "eval_error_accuracy": 0.8626242087113936,
      "eval_f1": 0.7973921765295887,
      "eval_loss": 0.25677669048309326,
      "eval_pr_auc": 0.8667069010917992,
      "eval_precision": 0.8298538622129437,
      "eval_recall": 0.7673745173745173,
      "eval_runtime": 7.1469,
      "eval_samples_per_second": 163.288,
      "eval_steps_per_second": 1.399,
      "step": 88
    }
  ],
  "logging_steps": 4,
  "max_steps": 380,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 16,
  "stateful_callbacks": {
    "MinEpochEarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.358268710518784e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}