checkpoint-675/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 675,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07407407407407407,
      "grad_norm": NaN,
      "learning_rate": 2.8911111111111114e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": NaN,
      "learning_rate": 2.78e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": NaN,
      "learning_rate": 2.668888888888889e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": NaN,
      "learning_rate": 2.5577777777777776e-05,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": NaN,
      "learning_rate": 2.4466666666666667e-05,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": NaN,
      "learning_rate": 2.3355555555555555e-05,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": NaN,
      "learning_rate": 2.2244444444444446e-05,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": NaN,
      "learning_rate": 2.1133333333333333e-05,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": NaN,
      "learning_rate": 2.0022222222222224e-05,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": NaN,
      "learning_rate": 1.891111111111111e-05,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": NaN,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": NaN,
      "learning_rate": 1.668888888888889e-05,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": NaN,
      "learning_rate": 1.557777777777778e-05,
      "loss": 0.0,
      "step": 650
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 5.5641,
      "eval_samples_per_second": 53.917,
      "eval_steps_per_second": 13.479,
      "step": 675
    }
  ],
  "logging_steps": 50,
  "max_steps": 1350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 501904362700800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}