{
  "best_metric": 9.694682121276855,
  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-750",
  "epoch": 2.0212192657460424,
  "eval_steps": 750,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "step": 742,
      "total_flos": 3.211629347340288e+16,
      "train_loss": 5.698867345434636,
      "train_runtime": 6114.1675,
      "train_samples_per_second": 15.538,
      "train_steps_per_second": 0.121
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.9989218328840974e-05,
      "loss": 10.3965,
      "step": 750
    },
    {
      "epoch": 1.01,
      "eval_loss": 9.694682121276855,
      "eval_runtime": 84.6491,
      "eval_samples_per_second": 59.067,
      "eval_steps_per_second": 0.933,
      "step": 750
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.897978436657682e-05,
      "loss": 4.9343,
      "step": 1500
    },
    {
      "epoch": 2.02,
      "eval_loss": 3.2859976291656494,
      "eval_runtime": 84.3631,
      "eval_samples_per_second": 59.268,
      "eval_steps_per_second": 0.936,
      "step": 1500
    }
  ],
  "logging_steps": 750,
  "max_steps": 37100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 750,
  "total_flos": 6.492241636356096e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}