{
  "best_metric": 1.1004505157470703,
  "best_model_checkpoint": "output_pipe/covid/origin/checkpoint-1000",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 1148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34843205574912894,
      "grad_norm": 174723.765625,
      "learning_rate": 2.8633879781420765e-05,
      "loss": 2.19,
      "step": 100
    },
    {
      "epoch": 0.6968641114982579,
      "grad_norm": 210712.359375,
      "learning_rate": 2.5901639344262294e-05,
      "loss": 2.0989,
      "step": 200
    },
    {
      "epoch": 0.6968641114982579,
      "eval_accuracy": 0.25943704996727035,
      "eval_f1": 0.23259103720824414,
      "eval_loss": 1.9880400896072388,
      "eval_matthews_correlation": 0.16738134005196834,
      "eval_precision": 0.3405661174127983,
      "eval_recall": 0.25091873792394775,
      "eval_runtime": 13.7172,
      "eval_samples_per_second": 668.212,
      "eval_steps_per_second": 2.624,
      "step": 200
    },
    {
      "epoch": 1.0452961672473868,
      "grad_norm": 251669.671875,
      "learning_rate": 2.3169398907103826e-05,
      "loss": 1.8143,
      "step": 300
    },
    {
      "epoch": 1.3937282229965158,
      "grad_norm": 211224.953125,
      "learning_rate": 2.0437158469945358e-05,
      "loss": 1.5479,
      "step": 400
    },
    {
      "epoch": 1.3937282229965158,
      "eval_accuracy": 0.43094043203142046,
      "eval_f1": 0.4387249414509633,
      "eval_loss": 1.5305389165878296,
      "eval_matthews_correlation": 0.35983899752446785,
      "eval_precision": 0.4808727141033031,
      "eval_recall": 0.4284813080538694,
      "eval_runtime": 13.9313,
      "eval_samples_per_second": 657.942,
      "eval_steps_per_second": 2.584,
      "step": 400
    },
    {
      "epoch": 1.7421602787456445,
      "grad_norm": 264649.65625,
      "learning_rate": 1.7704918032786887e-05,
      "loss": 1.411,
      "step": 500
    },
    {
      "epoch": 2.0905923344947737,
      "grad_norm": 225310.03125,
      "learning_rate": 1.4972677595628415e-05,
      "loss": 1.2811,
      "step": 600
    },
    {
      "epoch": 2.0905923344947737,
      "eval_accuracy": 0.5262928212960942,
      "eval_f1": 0.5325205291864618,
      "eval_loss": 1.297942042350769,
      "eval_matthews_correlation": 0.468070916526219,
      "eval_precision": 0.5588670157769567,
      "eval_recall": 0.5252968569339364,
      "eval_runtime": 13.9463,
      "eval_samples_per_second": 657.236,
      "eval_steps_per_second": 2.581,
      "step": 600
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 263688.8125,
      "learning_rate": 1.2240437158469946e-05,
      "loss": 1.1165,
      "step": 700
    },
    {
      "epoch": 2.7874564459930316,
      "grad_norm": 283741.96875,
      "learning_rate": 9.508196721311476e-06,
      "loss": 1.065,
      "step": 800
    },
    {
      "epoch": 2.7874564459930316,
      "eval_accuracy": 0.5775692777656557,
      "eval_f1": 0.578788427797142,
      "eval_loss": 1.1558705568313599,
      "eval_matthews_correlation": 0.524480876262069,
      "eval_precision": 0.592415806150315,
      "eval_recall": 0.5753616488335574,
      "eval_runtime": 13.9132,
      "eval_samples_per_second": 658.797,
      "eval_steps_per_second": 2.587,
      "step": 800
    },
    {
      "epoch": 3.1358885017421603,
      "grad_norm": 283403.375,
      "learning_rate": 6.775956284153006e-06,
      "loss": 0.9633,
      "step": 900
    },
    {
      "epoch": 3.484320557491289,
      "grad_norm": 259705.78125,
      "learning_rate": 4.043715846994535e-06,
      "loss": 0.8506,
      "step": 1000
    },
    {
      "epoch": 3.484320557491289,
      "eval_accuracy": 0.6014619245036003,
      "eval_f1": 0.6030440322941804,
      "eval_loss": 1.1004505157470703,
      "eval_matthews_correlation": 0.5509109398545572,
      "eval_precision": 0.6117691587329568,
      "eval_recall": 0.5997875750340463,
      "eval_runtime": 13.6202,
      "eval_samples_per_second": 672.972,
      "eval_steps_per_second": 2.643,
      "step": 1000
    },
    {
      "epoch": 3.832752613240418,
      "grad_norm": 272720.125,
      "learning_rate": 1.3114754098360657e-06,
      "loss": 0.8352,
      "step": 1100
    },
    {
      "epoch": 4.0,
      "step": 1148,
      "total_flos": 1.7099162793304202e+17,
      "train_loss": 1.3559243770426574,
      "train_runtime": 1444.1325,
      "train_samples_per_second": 203.125,
      "train_steps_per_second": 0.795
    }
  ],
  "logging_steps": 100,
  "max_steps": 1148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7099162793304202e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}