trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1673,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05977286312014345,
      "grad_norm": 0.18261943757534027,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.3555,
      "step": 100
    },
    {
      "epoch": 0.1195457262402869,
      "grad_norm": 0.2138003557920456,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.3285,
      "step": 200
    },
    {
      "epoch": 0.17931858936043035,
      "grad_norm": 0.3002658188343048,
      "learning_rate": 2e-05,
      "loss": 2.2489,
      "step": 300
    },
    {
      "epoch": 0.2390914524805738,
      "grad_norm": 0.4061976671218872,
      "learning_rate": 1.9739364808281564e-05,
      "loss": 2.1912,
      "step": 400
    },
    {
      "epoch": 0.2988643156007173,
      "grad_norm": 0.5177231431007385,
      "learning_rate": 1.8971045373758673e-05,
      "loss": 2.1328,
      "step": 500
    },
    {
      "epoch": 0.3586371787208607,
      "grad_norm": 0.6728057861328125,
      "learning_rate": 1.7735091913054898e-05,
      "loss": 2.062,
      "step": 600
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 0.6207203269004822,
      "learning_rate": 1.6095931019607367e-05,
      "loss": 2.0053,
      "step": 700
    },
    {
      "epoch": 0.4781829049611476,
      "grad_norm": 0.6931679248809814,
      "learning_rate": 1.4139007296160285e-05,
      "loss": 2.0062,
      "step": 800
    },
    {
      "epoch": 0.5379557680812911,
      "grad_norm": 0.6681210994720459,
      "learning_rate": 1.1966329380681454e-05,
      "loss": 1.9427,
      "step": 900
    },
    {
      "epoch": 0.5977286312014346,
      "grad_norm": 0.8678436279296875,
      "learning_rate": 9.691152538179525e-06,
      "loss": 1.9019,
      "step": 1000
    },
    {
      "epoch": 0.657501494321578,
      "grad_norm": 1.0380738973617554,
      "learning_rate": 7.432074999162258e-06,
      "loss": 1.9017,
      "step": 1100
    },
    {
      "epoch": 0.7172743574417214,
      "grad_norm": 0.8856862783432007,
      "learning_rate": 5.306855785127376e-06,
      "loss": 1.8821,
      "step": 1200
    },
    {
      "epoch": 0.7770472205618649,
      "grad_norm": 1.1661518812179565,
      "learning_rate": 3.426276279533615e-06,
      "loss": 1.8826,
      "step": 1300
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 0.8435269594192505,
      "learning_rate": 1.8883655223774121e-06,
      "loss": 1.8919,
      "step": 1400
    },
    {
      "epoch": 0.8965929468021518,
      "grad_norm": 0.7680924534797668,
      "learning_rate": 7.732902466662218e-07,
      "loss": 1.9126,
      "step": 1500
    },
    {
      "epoch": 0.9563658099222953,
      "grad_norm": 0.9946077466011047,
      "learning_rate": 1.3917602405313812e-07,
      "loss": 1.8853,
      "step": 1600
    },
    {
      "epoch": 1.0,
      "step": 1673,
      "total_flos": 3.0394718060544e+16,
      "train_loss": 2.029054084226035,
      "train_runtime": 519.4686,
      "train_samples_per_second": 6.439,
      "train_steps_per_second": 3.221
    }
  ],
  "logging_steps": 100,
  "max_steps": 1673,
  "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": 3.0394718060544e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}