trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3577017661524704,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.035770176615247035,
      "grad_norm": 0.2605220377445221,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 1.9177,
      "step": 10
    },
    {
      "epoch": 0.07154035323049407,
      "grad_norm": 0.29095056653022766,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.8015,
      "step": 20
    },
    {
      "epoch": 0.10731052984574112,
      "grad_norm": 0.2734232544898987,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.5329,
      "step": 30
    },
    {
      "epoch": 0.14308070646098814,
      "grad_norm": 0.3937128186225891,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.0377,
      "step": 40
    },
    {
      "epoch": 0.1788508830762352,
      "grad_norm": 0.08446656167507172,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 0.3894,
      "step": 50
    },
    {
      "epoch": 0.1788508830762352,
      "eval_loss": 0.2632354497909546,
      "eval_runtime": 681.8071,
      "eval_samples_per_second": 2.916,
      "eval_steps_per_second": 0.729,
      "step": 50
    },
    {
      "epoch": 0.21462105969148224,
      "grad_norm": 0.03653671219944954,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.2474,
      "step": 60
    },
    {
      "epoch": 0.25039123630672927,
      "grad_norm": 0.04479149729013443,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.2377,
      "step": 70
    },
    {
      "epoch": 0.2861614129219763,
      "grad_norm": 0.025527365505695343,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.2238,
      "step": 80
    },
    {
      "epoch": 0.32193158953722334,
      "grad_norm": 0.02618996612727642,
      "learning_rate": 9.920318725099602e-05,
      "loss": 0.2207,
      "step": 90
    },
    {
      "epoch": 0.3577017661524704,
      "grad_norm": 0.02924993820488453,
      "learning_rate": 9.787516600265605e-05,
      "loss": 0.214,
      "step": 100
    },
    {
      "epoch": 0.3577017661524704,
      "eval_loss": 0.211310014128685,
      "eval_runtime": 681.6444,
      "eval_samples_per_second": 2.916,
      "eval_steps_per_second": 0.729,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 837,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.243105825085456e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}