trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5014,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0997207818109294,
      "grad_norm": 2.346997022628784,
      "learning_rate": 4.5023932987634625e-05,
      "loss": 8.2424,
      "step": 500
    },
    {
      "epoch": 0.1994415636218588,
      "grad_norm": 2.3684158325195312,
      "learning_rate": 4.0037893897088155e-05,
      "loss": 7.6851,
      "step": 1000
    },
    {
      "epoch": 0.2991623454327882,
      "grad_norm": 3.409303665161133,
      "learning_rate": 3.5051854806541686e-05,
      "loss": 7.4872,
      "step": 1500
    },
    {
      "epoch": 0.3988831272437176,
      "grad_norm": 2.615360975265503,
      "learning_rate": 3.0065815715995216e-05,
      "loss": 7.344,
      "step": 2000
    },
    {
      "epoch": 0.49860390905464697,
      "grad_norm": 3.5242176055908203,
      "learning_rate": 2.5079776625448743e-05,
      "loss": 7.2749,
      "step": 2500
    },
    {
      "epoch": 0.5983246908655764,
      "grad_norm": 3.690262794494629,
      "learning_rate": 2.0093737534902273e-05,
      "loss": 7.1657,
      "step": 3000
    },
    {
      "epoch": 0.6980454726765057,
      "grad_norm": 2.940692663192749,
      "learning_rate": 1.5107698444355806e-05,
      "loss": 7.1298,
      "step": 3500
    },
    {
      "epoch": 0.7977662544874352,
      "grad_norm": 2.9132378101348877,
      "learning_rate": 1.0121659353809334e-05,
      "loss": 7.0938,
      "step": 4000
    },
    {
      "epoch": 0.8974870362983646,
      "grad_norm": 3.101921558380127,
      "learning_rate": 5.135620263262864e-06,
      "loss": 7.0715,
      "step": 4500
    },
    {
      "epoch": 0.9972078181092939,
      "grad_norm": 3.2258358001708984,
      "learning_rate": 1.495811727163941e-07,
      "loss": 7.0478,
      "step": 5000
    },
    {
      "epoch": 1.0,
      "step": 5014,
      "total_flos": 5279723050035456.0,
      "train_loss": 7.35303517095492,
      "train_runtime": 1261.9378,
      "train_samples_per_second": 63.568,
      "train_steps_per_second": 3.973
    }
  ],
  "logging_steps": 500,
  "max_steps": 5014,
  "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": 5279723050035456.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}