trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.060787502089570386,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012157500417914077,
      "eval_accuracy": 0.9978134671943089,
      "eval_f1": 0.5720789074355084,
      "eval_loss": NaN,
      "eval_precision": 0.5,
      "eval_recall": 0.6684397163120568,
      "eval_runtime": 6.301,
      "eval_samples_per_second": 8.094,
      "eval_steps_per_second": 8.094,
      "step": 100
    },
    {
      "epoch": 0.024315000835828153,
      "eval_accuracy": 0.9982138182714072,
      "eval_f1": 0.5731497418244406,
      "eval_loss": NaN,
      "eval_precision": 0.5568561872909699,
      "eval_recall": 0.5904255319148937,
      "eval_runtime": 6.4319,
      "eval_samples_per_second": 7.929,
      "eval_steps_per_second": 7.929,
      "step": 200
    },
    {
      "epoch": 0.03647250125374223,
      "eval_accuracy": 0.9982908088631569,
      "eval_f1": 0.5572232645403377,
      "eval_loss": NaN,
      "eval_precision": 0.5916334661354582,
      "eval_recall": 0.526595744680851,
      "eval_runtime": 6.4708,
      "eval_samples_per_second": 7.882,
      "eval_steps_per_second": 7.882,
      "step": 300
    },
    {
      "epoch": 0.048630001671656306,
      "eval_accuracy": 0.9986911599402553,
      "eval_f1": 0.6862416107382551,
      "eval_loss": NaN,
      "eval_precision": 0.6512738853503185,
      "eval_recall": 0.725177304964539,
      "eval_runtime": 6.2745,
      "eval_samples_per_second": 8.128,
      "eval_steps_per_second": 8.128,
      "step": 400
    },
    {
      "epoch": 0.060787502089570386,
      "grad_norm": 1.1875,
      "learning_rate": 9.39209726443769e-05,
      "loss": 0.044,
      "step": 500
    },
    {
      "epoch": 0.060787502089570386,
      "eval_accuracy": 0.9986449655852054,
      "eval_f1": 0.6560402684563759,
      "eval_loss": NaN,
      "eval_precision": 0.6226114649681529,
      "eval_recall": 0.6932624113475178,
      "eval_runtime": 8.7006,
      "eval_samples_per_second": 5.862,
      "eval_steps_per_second": 5.862,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 8225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 9176158363192776.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}