run-1/checkpoint-402/trainer_state.json

{
  "best_metric": 0.5147088719382571,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 402,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.47572973370552063,
      "eval_matthews_correlation": 0.44075455043157863,
      "eval_runtime": 0.7472,
      "eval_samples_per_second": 1395.808,
      "eval_steps_per_second": 88.325,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4667774438858032,
      "eval_matthews_correlation": 0.5147088719382571,
      "eval_runtime": 1.8072,
      "eval_samples_per_second": 577.142,
      "eval_steps_per_second": 36.521,
      "step": 268
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.570951521396637,
      "eval_matthews_correlation": 0.5075813582663956,
      "eval_runtime": 1.1406,
      "eval_samples_per_second": 914.446,
      "eval_steps_per_second": 57.865,
      "step": 402
    }
  ],
  "logging_steps": 500,
  "max_steps": 402,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 6.238111577485738e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 64,
    "seed": 5
  }
}