trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1233,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08110300081103,
      "grad_norm": 0.25841230154037476,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.3476,
      "step": 100
    },
    {
      "epoch": 0.16220600162206,
      "grad_norm": 0.2095279097557068,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.3349,
      "step": 200
    },
    {
      "epoch": 0.24330900243309003,
      "grad_norm": 0.3513042628765106,
      "learning_rate": 2e-05,
      "loss": 2.2524,
      "step": 300
    },
    {
      "epoch": 0.32441200324412,
      "grad_norm": 0.526100754737854,
      "learning_rate": 1.943843605129568e-05,
      "loss": 2.1266,
      "step": 400
    },
    {
      "epoch": 0.40551500405515006,
      "grad_norm": 0.6337389945983887,
      "learning_rate": 1.78168150188796e-05,
      "loss": 2.0207,
      "step": 500
    },
    {
      "epoch": 0.48661800486618007,
      "grad_norm": 0.8257550001144409,
      "learning_rate": 1.5317265684804865e-05,
      "loss": 1.9728,
      "step": 600
    },
    {
      "epoch": 0.5677210056772101,
      "grad_norm": 0.9637038111686707,
      "learning_rate": 1.222051940787633e-05,
      "loss": 1.901,
      "step": 700
    },
    {
      "epoch": 0.64882400648824,
      "grad_norm": 0.9433911442756653,
      "learning_rate": 8.874380401575476e-06,
      "loss": 1.886,
      "step": 800
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 0.9570260643959045,
      "learning_rate": 5.6546628725606675e-06,
      "loss": 1.8359,
      "step": 900
    },
    {
      "epoch": 0.8110300081103001,
      "grad_norm": 0.9578850269317627,
      "learning_rate": 2.9229822786931263e-06,
      "loss": 1.8447,
      "step": 1000
    },
    {
      "epoch": 0.8921330089213301,
      "grad_norm": 0.9690220952033997,
      "learning_rate": 9.861412881510891e-07,
      "loss": 1.804,
      "step": 1100
    },
    {
      "epoch": 0.9732360097323601,
      "grad_norm": 1.3679864406585693,
      "learning_rate": 6.167191586679556e-08,
      "loss": 1.8083,
      "step": 1200
    },
    {
      "epoch": 1.0,
      "step": 1233,
      "total_flos": 2.24075858706432e+16,
      "train_loss": 2.007913606493626,
      "train_runtime": 384.8783,
      "train_samples_per_second": 6.407,
      "train_steps_per_second": 3.204
    }
  ],
  "logging_steps": 100,
  "max_steps": 1233,
  "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": 2.24075858706432e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}