trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.975922953451043,
  "eval_steps": 1000,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2568218298555377,
      "grad_norm": 0.5769299172340473,
      "learning_rate": 9.980973490458728e-06,
      "loss": 0.488,
      "step": 10
    },
    {
      "epoch": 0.5136436597110754,
      "grad_norm": 0.3865011990286977,
      "learning_rate": 9.646737621134112e-06,
      "loss": 0.2453,
      "step": 20
    },
    {
      "epoch": 0.7704654895666132,
      "grad_norm": 0.310734122056056,
      "learning_rate": 8.92207832459788e-06,
      "loss": 0.2078,
      "step": 30
    },
    {
      "epoch": 1.0513643659711076,
      "grad_norm": 0.27685725084837776,
      "learning_rate": 7.86788218175523e-06,
      "loss": 0.2094,
      "step": 40
    },
    {
      "epoch": 1.3081861958266452,
      "grad_norm": 0.2898542558903432,
      "learning_rate": 6.572723780758069e-06,
      "loss": 0.172,
      "step": 50
    },
    {
      "epoch": 1.565008025682183,
      "grad_norm": 0.2771222768817642,
      "learning_rate": 5.145423593715558e-06,
      "loss": 0.165,
      "step": 60
    },
    {
      "epoch": 1.8218298555377208,
      "grad_norm": 0.272796424375955,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.1667,
      "step": 70
    },
    {
      "epoch": 2.102728731942215,
      "grad_norm": 0.3036563121854593,
      "learning_rate": 2.3751170983272e-06,
      "loss": 0.1759,
      "step": 80
    },
    {
      "epoch": 2.359550561797753,
      "grad_norm": 0.2787588519681375,
      "learning_rate": 1.264874643795021e-06,
      "loss": 0.1459,
      "step": 90
    },
    {
      "epoch": 2.6163723916532904,
      "grad_norm": 0.2846937852656666,
      "learning_rate": 4.6846106481675035e-07,
      "loss": 0.1483,
      "step": 100
    },
    {
      "epoch": 2.8731942215088284,
      "grad_norm": 0.2969477385850922,
      "learning_rate": 5.279180709527765e-08,
      "loss": 0.1451,
      "step": 110
    },
    {
      "epoch": 2.975922953451043,
      "step": 114,
      "total_flos": 425649635328000.0,
      "train_loss": 0.20393206257569163,
      "train_runtime": 6898.6432,
      "train_samples_per_second": 2.167,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 114,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 425649635328000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}