{
  "best_metric": 0.9596994535519126,
  "best_model_checkpoint": "train_authorship/train_outputs/05-25-2024_21:30:31/checkpoint-560",
  "epoch": 8.115942028985508,
  "eval_steps": 35,
  "global_step": 560,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.51,
      "grad_norm": 9.12179946899414,
      "learning_rate": 2.5362318840579714e-05,
      "loss": 0.9599,
      "step": 35
    },
    {
      "epoch": 0.51,
      "eval_acc_product": 0.522295927646477,
      "eval_fitzgerald_acc": 0.6823770491803278,
      "eval_hemingway_acc": 0.9651639344262295,
      "eval_loss": 0.4738686978816986,
      "eval_overall_acc": 0.8135245901639344,
      "eval_runtime": 13.1203,
      "eval_samples_per_second": 111.583,
      "eval_steps_per_second": 1.753,
      "eval_woolf_acc": 0.7930327868852459,
      "step": 35
    },
    {
      "epoch": 1.01,
      "grad_norm": 18.4027099609375,
      "learning_rate": 4.99194847020934e-05,
      "loss": 0.3839,
      "step": 70
    },
    {
      "epoch": 1.01,
      "eval_acc_product": 0.7210372836134964,
      "eval_fitzgerald_acc": 0.764344262295082,
      "eval_hemingway_acc": 0.9815573770491803,
      "eval_loss": 0.24899350106716156,
      "eval_overall_acc": 0.9023224043715847,
      "eval_runtime": 13.1386,
      "eval_samples_per_second": 111.428,
      "eval_steps_per_second": 1.751,
      "eval_woolf_acc": 0.9610655737704918,
      "step": 70
    },
    {
      "epoch": 1.52,
      "grad_norm": 7.836585998535156,
      "learning_rate": 4.710144927536232e-05,
      "loss": 0.2387,
      "step": 105
    },
    {
      "epoch": 1.52,
      "eval_acc_product": 0.8025821475696203,
      "eval_fitzgerald_acc": 0.9631147540983607,
      "eval_hemingway_acc": 0.9221311475409836,
      "eval_loss": 0.20742054283618927,
      "eval_overall_acc": 0.9296448087431693,
      "eval_runtime": 13.1443,
      "eval_samples_per_second": 111.379,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.9036885245901639,
      "step": 105
    },
    {
      "epoch": 2.03,
      "grad_norm": 10.438405990600586,
      "learning_rate": 4.428341384863124e-05,
      "loss": 0.1938,
      "step": 140
    },
    {
      "epoch": 2.03,
      "eval_acc_product": 0.8229529244050163,
      "eval_fitzgerald_acc": 0.9528688524590164,
      "eval_hemingway_acc": 0.9733606557377049,
      "eval_loss": 0.2009282410144806,
      "eval_overall_acc": 0.9378415300546448,
      "eval_runtime": 13.1419,
      "eval_samples_per_second": 111.399,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.8872950819672131,
      "step": 140
    },
    {
      "epoch": 2.54,
      "grad_norm": 11.882472038269043,
      "learning_rate": 4.146537842190016e-05,
      "loss": 0.1373,
      "step": 175
    },
    {
      "epoch": 2.54,
      "eval_acc_product": 0.8087266940845269,
      "eval_fitzgerald_acc": 0.9467213114754098,
      "eval_hemingway_acc": 0.8831967213114754,
      "eval_loss": 0.20678555965423584,
      "eval_overall_acc": 0.9323770491803278,
      "eval_runtime": 13.1478,
      "eval_samples_per_second": 111.35,
      "eval_steps_per_second": 1.749,
      "eval_woolf_acc": 0.9672131147540983,
      "step": 175
    },
    {
      "epoch": 3.04,
      "grad_norm": 3.76464581489563,
      "learning_rate": 3.864734299516908e-05,
      "loss": 0.0751,
      "step": 210
    },
    {
      "epoch": 3.04,
      "eval_acc_product": 0.8355915183980156,
      "eval_fitzgerald_acc": 0.8913934426229508,
      "eval_hemingway_acc": 0.9774590163934426,
      "eval_loss": 0.21373361349105835,
      "eval_overall_acc": 0.9426229508196722,
      "eval_runtime": 13.1464,
      "eval_samples_per_second": 111.361,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.9590163934426229,
      "step": 210
    },
    {
      "epoch": 3.55,
      "grad_norm": 7.145068168640137,
      "learning_rate": 3.5829307568438e-05,
      "loss": 0.0799,
      "step": 245
    },
    {
      "epoch": 3.55,
      "eval_acc_product": 0.8595802071539027,
      "eval_fitzgerald_acc": 0.9467213114754098,
      "eval_hemingway_acc": 0.9508196721311475,
      "eval_loss": 0.19885893166065216,
      "eval_overall_acc": 0.9508196721311475,
      "eval_runtime": 13.143,
      "eval_samples_per_second": 111.39,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.9549180327868853,
      "step": 245
    },
    {
      "epoch": 4.06,
      "grad_norm": 19.213457107543945,
      "learning_rate": 3.301127214170693e-05,
      "loss": 0.0689,
      "step": 280
    },
    {
      "epoch": 4.06,
      "eval_acc_product": 0.720976809113428,
      "eval_fitzgerald_acc": 0.985655737704918,
      "eval_hemingway_acc": 0.9036885245901639,
      "eval_loss": 0.44272100925445557,
      "eval_overall_acc": 0.8995901639344263,
      "eval_runtime": 13.1467,
      "eval_samples_per_second": 111.359,
      "eval_steps_per_second": 1.749,
      "eval_woolf_acc": 0.8094262295081968,
      "step": 280
    },
    {
      "epoch": 4.57,
      "grad_norm": 18.969886779785156,
      "learning_rate": 3.0193236714975848e-05,
      "loss": 0.0514,
      "step": 315
    },
    {
      "epoch": 4.57,
      "eval_acc_product": 0.8326357712760099,
      "eval_fitzgerald_acc": 0.9139344262295082,
      "eval_hemingway_acc": 0.9836065573770492,
      "eval_loss": 0.3214350938796997,
      "eval_overall_acc": 0.9412568306010929,
      "eval_runtime": 13.1454,
      "eval_samples_per_second": 111.37,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.9262295081967213,
      "step": 315
    },
    {
      "epoch": 5.07,
      "grad_norm": 3.789048433303833,
      "learning_rate": 2.7375201288244768e-05,
      "loss": 0.0247,
      "step": 350
    },
    {
      "epoch": 5.07,
      "eval_acc_product": 0.8625536629442553,
      "eval_fitzgerald_acc": 0.9200819672131147,
      "eval_hemingway_acc": 0.9651639344262295,
      "eval_loss": 0.282697856426239,
      "eval_overall_acc": 0.9521857923497268,
      "eval_runtime": 13.1482,
      "eval_samples_per_second": 111.346,
      "eval_steps_per_second": 1.749,
      "eval_woolf_acc": 0.9713114754098361,
      "step": 350
    },
    {
      "epoch": 5.58,
      "grad_norm": 0.13263003528118134,
      "learning_rate": 2.455716586151369e-05,
      "loss": 0.0061,
      "step": 385
    },
    {
      "epoch": 5.58,
      "eval_acc_product": 0.870603844594922,
      "eval_fitzgerald_acc": 0.9508196721311475,
      "eval_hemingway_acc": 0.9692622950819673,
      "eval_loss": 0.28144514560699463,
      "eval_overall_acc": 0.9549180327868853,
      "eval_runtime": 13.1424,
      "eval_samples_per_second": 111.395,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.944672131147541,
      "step": 385
    },
    {
      "epoch": 6.09,
      "grad_norm": 0.01614902913570404,
      "learning_rate": 2.173913043478261e-05,
      "loss": 0.017,
      "step": 420
    },
    {
      "epoch": 6.09,
      "eval_acc_product": 0.8501492828694912,
      "eval_fitzgerald_acc": 0.9528688524590164,
      "eval_hemingway_acc": 0.930327868852459,
      "eval_loss": 0.34684956073760986,
      "eval_overall_acc": 0.9474043715846995,
      "eval_runtime": 13.1477,
      "eval_samples_per_second": 111.35,
      "eval_steps_per_second": 1.749,
      "eval_woolf_acc": 0.9590163934426229,
      "step": 420
    },
    {
      "epoch": 6.59,
      "grad_norm": 0.007705519441515207,
      "learning_rate": 1.892109500805153e-05,
      "loss": 0.0108,
      "step": 455
    },
    {
      "epoch": 6.59,
      "eval_acc_product": 0.8705621113386143,
      "eval_fitzgerald_acc": 0.9385245901639344,
      "eval_hemingway_acc": 0.9651639344262295,
      "eval_loss": 0.26387327909469604,
      "eval_overall_acc": 0.9549180327868853,
      "eval_runtime": 13.1463,
      "eval_samples_per_second": 111.362,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.9610655737704918,
      "step": 455
    },
    {
      "epoch": 7.1,
      "grad_norm": 0.04329540580511093,
      "learning_rate": 1.610305958132045e-05,
      "loss": 0.0237,
      "step": 490
    },
    {
      "epoch": 7.1,
      "eval_acc_product": 0.8607751722611143,
      "eval_fitzgerald_acc": 0.9426229508196722,
      "eval_hemingway_acc": 0.9815573770491803,
      "eval_loss": 0.32457903027534485,
      "eval_overall_acc": 0.9515027322404371,
      "eval_runtime": 13.1416,
      "eval_samples_per_second": 111.402,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.930327868852459,
      "step": 490
    },
    {
      "epoch": 7.61,
      "grad_norm": 18.448688507080078,
      "learning_rate": 1.3285024154589374e-05,
      "loss": 0.0109,
      "step": 525
    },
    {
      "epoch": 7.61,
      "eval_acc_product": 0.8574545818262321,
      "eval_fitzgerald_acc": 0.9569672131147541,
      "eval_hemingway_acc": 0.9631147540983607,
      "eval_loss": 0.32199960947036743,
      "eval_overall_acc": 0.950136612021858,
      "eval_runtime": 13.141,
      "eval_samples_per_second": 111.407,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.930327868852459,
      "step": 525
    },
    {
      "epoch": 8.12,
      "grad_norm": 0.07037464529275894,
      "learning_rate": 1.0466988727858294e-05,
      "loss": 0.0108,
      "step": 560
    },
    {
      "epoch": 8.12,
      "eval_acc_product": 0.8835792216639279,
      "eval_fitzgerald_acc": 0.9385245901639344,
      "eval_hemingway_acc": 0.9692622950819673,
      "eval_loss": 0.27515432238578796,
      "eval_overall_acc": 0.9596994535519126,
      "eval_runtime": 13.1404,
      "eval_samples_per_second": 111.412,
      "eval_steps_per_second": 1.75,
      "eval_woolf_acc": 0.9713114754098361,
      "step": 560
    }
  ],
  "logging_steps": 35,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 35,
  "total_flos": 1.4725988675974908e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}