run-14/checkpoint-2874/trainer_state.json

{
  "best_metric": 0.8711151736745887,
  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-14\\checkpoint-2874",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2874,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2.5401671139683948e-05,
      "loss": 0.4836,
      "step": 958
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8569469835466179,
      "eval_loss": 0.4813261330127716,
      "eval_runtime": 10.7519,
      "eval_samples_per_second": 203.5,
      "eval_steps_per_second": 1.674,
      "step": 958
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2700835569841974e-05,
      "loss": 0.4612,
      "step": 1916
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8692870201096892,
      "eval_loss": 0.47166088223457336,
      "eval_runtime": 10.8589,
      "eval_samples_per_second": 201.494,
      "eval_steps_per_second": 1.658,
      "step": 1916
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.4553,
      "step": 2874
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8711151736745887,
      "eval_loss": 0.4716881811618805,
      "eval_runtime": 10.8282,
      "eval_samples_per_second": 202.065,
      "eval_steps_per_second": 1.662,
      "step": 2874
    }
  ],
  "logging_steps": 500,
  "max_steps": 2874,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2945207254752.0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.810250670952592e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 8,
    "seed": 24
  }
}