checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9920318725099602,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.398406374501992,
      "grad_norm": 8.759617805480957,
      "learning_rate": 1.7343957503320053e-05,
      "loss": 0.8369,
      "step": 100
    },
    {
      "epoch": 0.796812749003984,
      "grad_norm": 34.44209671020508,
      "learning_rate": 1.4687915006640108e-05,
      "loss": 0.1261,
      "step": 200
    },
    {
      "epoch": 1.1952191235059761,
      "grad_norm": 0.7429738640785217,
      "learning_rate": 1.2031872509960161e-05,
      "loss": 0.056,
      "step": 300
    },
    {
      "epoch": 1.593625498007968,
      "grad_norm": 0.08053913712501526,
      "learning_rate": 9.375830013280214e-06,
      "loss": 0.0606,
      "step": 400
    },
    {
      "epoch": 1.9920318725099602,
      "grad_norm": 0.04419610649347305,
      "learning_rate": 6.719787516600266e-06,
      "loss": 0.0523,
      "step": 500
    },
    {
      "epoch": 1.9920318725099602,
      "eval_accuracy": 0.9820627802690582,
      "eval_f1": 0.9819921426216374,
      "eval_loss": 0.126918762922287,
      "eval_precision": 0.9824181570038463,
      "eval_recall": 0.9820627802690582,
      "eval_runtime": 97.4831,
      "eval_samples_per_second": 2.288,
      "eval_steps_per_second": 0.287,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 753,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 262723465250304.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}