checkpoint-61/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 61,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 510.73779296875,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 57.8051,
      "step": 10
    },
    {
      "epoch": 0.33195020746887965,
      "grad_norm": 497.617919921875,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 55.2954,
      "step": 20
    },
    {
      "epoch": 0.4979253112033195,
      "grad_norm": 415.9478454589844,
      "learning_rate": 5.8e-06,
      "loss": 47.3195,
      "step": 30
    },
    {
      "epoch": 0.6639004149377593,
      "grad_norm": 376.719970703125,
      "learning_rate": 7.800000000000002e-06,
      "loss": 37.9815,
      "step": 40
    },
    {
      "epoch": 0.8298755186721992,
      "grad_norm": 322.2588195800781,
      "learning_rate": 9.800000000000001e-06,
      "loss": 30.5138,
      "step": 50
    },
    {
      "epoch": 0.995850622406639,
      "grad_norm": 324.34747314453125,
      "learning_rate": 1.18e-05,
      "loss": 26.6713,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 61,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}