run-0/checkpoint-1290/trainer_state.json

{
  "best_metric": 0.8898797983714618,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-645",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1290,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.770919680595398,
      "learning_rate": 0.00045575725544182215,
      "loss": 0.2361,
      "step": 645
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8898797983714618,
      "eval_f1": 0.003508771929824561,
      "eval_loss": 0.22947192192077637,
      "eval_mcc": 0.039546160983878816,
      "eval_precision": 1.0,
      "eval_recall": 0.0017574692442882249,
      "eval_runtime": 9.9701,
      "eval_samples_per_second": 517.345,
      "eval_steps_per_second": 16.249,
      "step": 645
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8797195553779602,
      "learning_rate": 0.00040511756039273084,
      "loss": 0.2287,
      "step": 1290
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8896859247770453,
      "eval_f1": 0.0,
      "eval_loss": 0.22863532602787018,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 10.133,
      "eval_samples_per_second": 509.028,
      "eval_steps_per_second": 15.987,
      "step": 1290
    }
  ],
  "logging_steps": 500,
  "max_steps": 6450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 3173885065200.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6185480031675171,
    "learning_rate": 0.0005063969504909135,
    "num_train_epochs": 10,
    "temperature": 26
  }
}