checkpoint-375/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.9283596873283386,
      "learning_rate": 3e-05,
      "loss": 1.963,
      "step": 100
    },
    {
      "epoch": 0.9973333333333333,
      "eval_accuracy": 0.5695384615384615,
      "eval_loss": 1.6438876390457153,
      "eval_runtime": 5.0534,
      "eval_samples_per_second": 98.943,
      "eval_steps_per_second": 12.467,
      "step": 187
    },
    {
      "epoch": 0.9973333333333333,
      "eval_exact_match": 16.2,
      "eval_f1": 25.888571428571442,
      "step": 187
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 1.0407154560089111,
      "learning_rate": 3e-05,
      "loss": 1.6668,
      "step": 200
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.1281720399856567,
      "learning_rate": 3e-05,
      "loss": 1.6099,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5733333333333334,
      "eval_loss": 1.618270754814148,
      "eval_runtime": 5.1983,
      "eval_samples_per_second": 96.186,
      "eval_steps_per_second": 12.119,
      "step": 375
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 16.6,
      "eval_f1": 26.287619047619057,
      "step": 375
    }
  ],
  "logging_steps": 100,
  "max_steps": 9350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6864138500308992.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}