checkpoint-25/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.49261083743842365,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 0.3509202003479004,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.8235,
      "step": 5
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.3276345431804657,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.893,
      "step": 10
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 0.3548250198364258,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8663,
      "step": 15
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.37671414017677307,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.6304,
      "step": 20
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.32981401681900024,
      "learning_rate": 0.0,
      "loss": 0.7979,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 25,
  "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": 2425255585247232.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}