run-m4sjb92w/checkpoint-25/trainer_state.json

{
  "best_metric": 0.6523297491039427,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-m4sjb92w/checkpoint-25",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.5911545753479004,
      "learning_rate": 3.072424541935991e-05,
      "loss": 0.5559,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.1426916122436523,
      "learning_rate": 1.0241415139786638e-05,
      "loss": 0.4676,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7575,
      "eval_f1": 0.6523297491039427,
      "eval_loss": 0.45884665846824646,
      "eval_precision": 0.5833333333333334,
      "eval_recall": 0.7398373983739838,
      "eval_runtime": 1.5883,
      "eval_samples_per_second": 251.842,
      "eval_steps_per_second": 15.74,
      "step": 25
    }
  ],
  "logging_steps": 10,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 169558270279680.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 5.1207075698933185e-05,
    "metric": "eval/loss",
    "num_train_epochs": 1,
    "per_device_train_batch_size": 64,
    "seed": 18
  }
}