{
  "best_global_step": 162645,
  "best_metric": 0.75,
  "best_model_checkpoint": "models/NED/MedMentions_human_only_tfidf_hybrid_long_v2_addheaders/Llama-3.1-8B-Instruct/checkpoint-162645",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 162645,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.3341667487071673,
      "epoch": 1.0,
      "grad_norm": 210.0,
      "learning_rate": 1.99991802270771e-05,
      "loss": 0.6196,
      "mean_token_accuracy": 0.8641792057390866,
      "num_tokens": 128523013.0,
      "step": 32529
    },
    {
      "epoch": 1.0,
      "eval_entropy": 1.421211676299572,
      "eval_loss": 0.41451308131217957,
      "eval_mean_token_accuracy": 0.898672553896904,
      "eval_num_gold": 400,
      "eval_num_guess": 400,
      "eval_num_tokens": 128523013.0,
      "eval_recall": 0.7225,
      "eval_runtime": 12.958,
      "eval_samples_per_second": 30.869,
      "eval_steps_per_second": 6.174,
      "step": 32529
    },
    {
      "entropy": 1.0824028312080687,
      "epoch": 2.0,
      "grad_norm": 44.0,
      "learning_rate": 2.9690750074794507e-05,
      "loss": 0.2808,
      "mean_token_accuracy": 0.9327123904494635,
      "num_tokens": 257046026.0,
      "step": 65058
    },
    {
      "epoch": 2.0,
      "eval_entropy": 1.1366001389920712,
      "eval_loss": 0.5472019910812378,
      "eval_mean_token_accuracy": 0.9010569922626018,
      "eval_num_gold": 400,
      "eval_num_guess": 400,
      "eval_num_tokens": 257046026.0,
      "eval_recall": 0.7425,
      "eval_runtime": 12.8244,
      "eval_samples_per_second": 31.191,
      "eval_steps_per_second": 6.238,
      "step": 65058
    },
    {
      "entropy": 0.8375838961411133,
      "epoch": 3.0,
      "grad_norm": 0.24609375,
      "learning_rate": 2.9072193177726957e-05,
      "loss": 0.1261,
      "mean_token_accuracy": 0.9708323454896451,
      "num_tokens": 128523013.0,
      "step": 97587
    },
    {
      "epoch": 3.0,
      "eval_entropy": 0.8833060540258885,
      "eval_loss": 0.5918775796890259,
      "eval_mean_token_accuracy": 0.9003275491297245,
      "eval_num_gold": 400,
      "eval_num_guess": 400,
      "eval_num_tokens": 128523013.0,
      "eval_recall": 0.7375,
      "eval_runtime": 12.8454,
      "eval_samples_per_second": 31.14,
      "eval_steps_per_second": 6.228,
      "step": 97587
    },
    {
      "entropy": 0.6976695484764193,
      "epoch": 4.0,
      "grad_norm": 0.050537109375,
      "learning_rate": 2.845363628065941e-05,
      "loss": 0.0463,
      "mean_token_accuracy": 0.9893607802650367,
      "num_tokens": 257046026.0,
      "step": 130116
    },
    {
      "epoch": 4.0,
      "eval_entropy": 0.7260291546583175,
      "eval_loss": 0.7683401703834534,
      "eval_mean_token_accuracy": 0.9001270815730095,
      "eval_num_gold": 400,
      "eval_num_guess": 400,
      "eval_num_tokens": 257046026.0,
      "eval_recall": 0.7425,
      "eval_runtime": 12.7469,
      "eval_samples_per_second": 31.38,
      "eval_steps_per_second": 6.276,
      "step": 130116
    },
    {
      "entropy": 0.6267366673389785,
      "epoch": 5.0,
      "grad_norm": 0.000751495361328125,
      "learning_rate": 2.7835079383591863e-05,
      "loss": 0.014,
      "mean_token_accuracy": 0.9968704790790366,
      "num_tokens": 128523013.0,
      "step": 162645
    },
    {
      "epoch": 5.0,
      "eval_entropy": 0.6898447863757611,
      "eval_loss": 0.8766273260116577,
      "eval_mean_token_accuracy": 0.8994662061333656,
      "eval_num_gold": 400,
      "eval_num_guess": 400,
      "eval_num_tokens": 128523013.0,
      "eval_recall": 0.75,
      "eval_runtime": 13.1668,
      "eval_samples_per_second": 30.38,
      "eval_steps_per_second": 6.076,
      "step": 162645
    }
  ],
  "logging_steps": 0,
  "max_steps": 1626450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8936680388239032e+19,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}