trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.905829596412556,
  "eval_steps": 500,
  "global_step": 1700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11210762331838565,
      "grad_norm": 2.0963618755340576,
      "learning_rate": 2.793296089385475e-05,
      "loss": 4.9671,
      "step": 100
    },
    {
      "epoch": 0.2242152466367713,
      "grad_norm": 0.3255109190940857,
      "learning_rate": 4.9408099688473526e-05,
      "loss": 4.7197,
      "step": 200
    },
    {
      "epoch": 0.336322869955157,
      "grad_norm": 1.1150901317596436,
      "learning_rate": 4.632398753894081e-05,
      "loss": 4.5727,
      "step": 300
    },
    {
      "epoch": 0.4484304932735426,
      "grad_norm": 4.738381862640381,
      "learning_rate": 4.320872274143302e-05,
      "loss": 4.5585,
      "step": 400
    },
    {
      "epoch": 0.5605381165919282,
      "grad_norm": 0.3568013906478882,
      "learning_rate": 4.0093457943925236e-05,
      "loss": 4.5399,
      "step": 500
    },
    {
      "epoch": 0.672645739910314,
      "grad_norm": 0.558647871017456,
      "learning_rate": 3.700934579439253e-05,
      "loss": 4.4905,
      "step": 600
    },
    {
      "epoch": 0.7847533632286996,
      "grad_norm": 19.64227867126465,
      "learning_rate": 3.3894080996884734e-05,
      "loss": 4.4371,
      "step": 700
    },
    {
      "epoch": 0.8968609865470852,
      "grad_norm": 2.4077465534210205,
      "learning_rate": 3.077881619937695e-05,
      "loss": 4.4867,
      "step": 800
    },
    {
      "epoch": 1.0089686098654709,
      "grad_norm": 1.3140878677368164,
      "learning_rate": 2.7663551401869157e-05,
      "loss": 4.4675,
      "step": 900
    },
    {
      "epoch": 1.1210762331838564,
      "grad_norm": 1.7104419469833374,
      "learning_rate": 2.4579439252336452e-05,
      "loss": 4.432,
      "step": 1000
    },
    {
      "epoch": 1.2331838565022422,
      "grad_norm": 7.763595104217529,
      "learning_rate": 2.1464174454828662e-05,
      "loss": 4.4185,
      "step": 1100
    },
    {
      "epoch": 1.3452914798206277,
      "grad_norm": 0.4148617088794708,
      "learning_rate": 1.8348909657320872e-05,
      "loss": 4.428,
      "step": 1200
    },
    {
      "epoch": 1.4573991031390134,
      "grad_norm": 2.4640185832977295,
      "learning_rate": 1.5233644859813085e-05,
      "loss": 4.4133,
      "step": 1300
    },
    {
      "epoch": 1.5695067264573992,
      "grad_norm": 0.4486638903617859,
      "learning_rate": 1.2118380062305297e-05,
      "loss": 4.3019,
      "step": 1400
    },
    {
      "epoch": 1.6816143497757847,
      "grad_norm": 191.92808532714844,
      "learning_rate": 9.003115264797508e-06,
      "loss": 4.4209,
      "step": 1500
    },
    {
      "epoch": 1.7937219730941703,
      "grad_norm": 2.8736190795898438,
      "learning_rate": 5.88785046728972e-06,
      "loss": 4.3696,
      "step": 1600
    },
    {
      "epoch": 1.905829596412556,
      "grad_norm": 0.13583791255950928,
      "learning_rate": 2.7725856697819316e-06,
      "loss": 4.3962,
      "step": 1700
    }
  ],
  "logging_steps": 100,
  "max_steps": 1784,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}