{
  "best_metric": 1.9211012125015259,
  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3000",
  "epoch": 5.052206130010104,
  "eval_steps": 750,
  "global_step": 3750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.01,
      "learning_rate": 4.949460916442048e-05,
      "loss": 5.4,
      "step": 750
    },
    {
      "epoch": 1.01,
      "eval_loss": 3.985283613204956,
      "eval_runtime": 84.6074,
      "eval_samples_per_second": 59.096,
      "eval_steps_per_second": 0.934,
      "step": 750
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.8989218328840976e-05,
      "loss": 3.3737,
      "step": 1500
    },
    {
      "epoch": 2.02,
      "eval_loss": 2.947718858718872,
      "eval_runtime": 84.1622,
      "eval_samples_per_second": 59.409,
      "eval_steps_per_second": 0.939,
      "step": 1500
    },
    {
      "epoch": 3.03,
      "learning_rate": 4.84845013477089e-05,
      "loss": 2.5551,
      "step": 2250
    },
    {
      "epoch": 3.03,
      "eval_loss": 2.259490728378296,
      "eval_runtime": 84.2333,
      "eval_samples_per_second": 59.359,
      "eval_steps_per_second": 0.938,
      "step": 2250
    },
    {
      "epoch": 4.04,
      "learning_rate": 4.7979110512129385e-05,
      "loss": 2.0321,
      "step": 3000
    },
    {
      "epoch": 4.04,
      "eval_loss": 1.9211012125015259,
      "eval_runtime": 84.2271,
      "eval_samples_per_second": 59.363,
      "eval_steps_per_second": 0.938,
      "step": 3000
    },
    {
      "epoch": 5.05,
      "learning_rate": 4.7473719676549865e-05,
      "loss": 1.6766,
      "step": 3750
    },
    {
      "epoch": 5.05,
      "eval_loss": 1.6346299648284912,
      "eval_runtime": 84.1885,
      "eval_samples_per_second": 59.391,
      "eval_steps_per_second": 0.938,
      "step": 3750
    }
  ],
  "logging_steps": 750,
  "max_steps": 74200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 750,
  "total_flos": 1.622992778754048e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}