run-7/checkpoint-16/trainer_state.json

{
  "best_metric": 0.7326732673267327,
  "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-7/checkpoint-8",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.62,
      "grad_norm": 0.9305598735809326,
      "learning_rate": 1.0388926727261681e-05,
      "loss": 0.6973,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.68402099609375,
      "eval_runtime": 1.3601,
      "eval_samples_per_second": 47.054,
      "eval_steps_per_second": 5.882,
      "step": 8
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.470983624458313,
      "learning_rate": 1.6160552686851503e-05,
      "loss": 0.6748,
      "step": 10
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.3902422785758972,
      "learning_rate": 1.5006227494933539e-05,
      "loss": 0.6423,
      "step": 15
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.6836051940917969,
      "eval_runtime": 1.3646,
      "eval_samples_per_second": 46.9,
      "eval_steps_per_second": 5.863,
      "step": 16
    }
  ],
  "logging_steps": 5,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2022063066922848.0,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.662228276361869e-05,
    "per_device_train_batch_size": 24
  }
}