trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9968051118210862,
  "eval_steps": 500,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06389776357827476,
      "learning_rate": 0.00019945941475610623,
      "loss": 12.3944,
      "step": 10
    },
    {
      "epoch": 0.12779552715654952,
      "learning_rate": 0.00019516973750305532,
      "loss": 8.3174,
      "step": 20
    },
    {
      "epoch": 0.19169329073482427,
      "learning_rate": 0.00018677539646179707,
      "loss": 6.6539,
      "step": 30
    },
    {
      "epoch": 0.25559105431309903,
      "learning_rate": 0.00017463843894486937,
      "loss": 5.7949,
      "step": 40
    },
    {
      "epoch": 0.3194888178913738,
      "learning_rate": 0.0001592823310385073,
      "loss": 5.2228,
      "step": 50
    },
    {
      "epoch": 0.38338658146964855,
      "learning_rate": 0.00014136938054879283,
      "loss": 4.8737,
      "step": 60
    },
    {
      "epoch": 0.4472843450479233,
      "learning_rate": 0.00012167217171462566,
      "loss": 4.7285,
      "step": 70
    },
    {
      "epoch": 0.5111821086261981,
      "learning_rate": 0.00010104024370624644,
      "loss": 4.4254,
      "step": 80
    },
    {
      "epoch": 0.5750798722044729,
      "learning_rate": 8.036345006322359e-05,
      "loss": 4.2315,
      "step": 90
    },
    {
      "epoch": 0.6389776357827476,
      "learning_rate": 6.053357937665237e-05,
      "loss": 4.1113,
      "step": 100
    },
    {
      "epoch": 0.7028753993610224,
      "learning_rate": 4.240589251272342e-05,
      "loss": 4.1268,
      "step": 110
    },
    {
      "epoch": 0.7667731629392971,
      "learning_rate": 2.6762235274383772e-05,
      "loss": 3.9841,
      "step": 120
    },
    {
      "epoch": 0.8306709265175719,
      "learning_rate": 1.4277317449282834e-05,
      "loss": 3.9334,
      "step": 130
    },
    {
      "epoch": 0.8945686900958466,
      "learning_rate": 5.489612626189245e-06,
      "loss": 3.9335,
      "step": 140
    },
    {
      "epoch": 0.9584664536741214,
      "learning_rate": 7.781338686584927e-07,
      "loss": 3.9228,
      "step": 150
    },
    {
      "epoch": 0.9968051118210862,
      "step": 156,
      "total_flos": 1.0008434413928448e+16,
      "train_loss": 5.322952857384315,
      "train_runtime": 598.9134,
      "train_samples_per_second": 8.348,
      "train_steps_per_second": 0.26
    }
  ],
  "logging_steps": 10,
  "max_steps": 156,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 999999,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0008434413928448e+16,
  "train_batch_size": null,
  "trial_name": null,
  "trial_params": null
}