trainer_state.json

{
  "best_metric": 0.6542556881904602,
  "best_model_checkpoint": "output_pipe/H3K9ac/origin/checkpoint-200",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 348,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1494252873563218,
      "grad_norm": 171036.0625,
      "learning_rate": 2.4966442953020137e-05,
      "loss": 0.6027,
      "step": 100
    },
    {
      "epoch": 2.2988505747126435,
      "grad_norm": 187976.71875,
      "learning_rate": 1.4899328859060403e-05,
      "loss": 0.4556,
      "step": 200
    },
    {
      "epoch": 2.2988505747126435,
      "eval_accuracy": 0.6970133141417776,
      "eval_f1": 0.695222854606308,
      "eval_loss": 0.6542556881904602,
      "eval_matthews_correlation": 0.4314315523884532,
      "eval_precision": 0.7215611344688307,
      "eval_recall": 0.7100246336553399,
      "eval_runtime": 2.1578,
      "eval_samples_per_second": 1287.9,
      "eval_steps_per_second": 5.098,
      "step": 200
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 224515.515625,
      "learning_rate": 4.832214765100671e-06,
      "loss": 0.2304,
      "step": 300
    },
    {
      "epoch": 4.0,
      "step": 348,
      "total_flos": 2.1990897446265216e+16,
      "train_loss": 0.38522801591062,
      "train_runtime": 211.1471,
      "train_samples_per_second": 421.015,
      "train_steps_per_second": 1.648
    }
  ],
  "logging_steps": 100,
  "max_steps": 348,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1990897446265216e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}