trainer_state.json

{
  "best_metric": 0.8178452253341675,
  "best_model_checkpoint": "./results/run-a80efcad/checkpoint-344",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 688,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029069767441860465,
      "grad_norm": 1.1931110620498657,
      "learning_rate": 1.1782500918571267e-07,
      "loss": 1.0951,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.621996151996152,
      "eval_loss": 0.8178452253341675,
      "eval_runtime": 1.0,
      "eval_samples_per_second": 1831.952,
      "eval_steps_per_second": 228.994,
      "step": 344
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.6674442219731551,
      "eval_loss": 0.8049888014793396,
      "eval_runtime": 0.9934,
      "eval_samples_per_second": 1844.13,
      "eval_steps_per_second": 230.516,
      "step": 688
    }
  ],
  "logging_steps": 1000,
  "max_steps": 688,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4209814683648.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.9456252296428165e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 16,
    "warmup_steps": 250,
    "weight_decay": 0.22747954091633416
  }
}