trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17041581458759372,
  "eval_steps": 500,
  "global_step": 8500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01002445968162316,
      "grad_norm": 0.27810075879096985,
      "learning_rate": 2.969926620955131e-05,
      "loss": 0.0283,
      "step": 500
    },
    {
      "epoch": 0.02004891936324632,
      "grad_norm": 0.32781505584716797,
      "learning_rate": 2.939853241910261e-05,
      "loss": 0.0244,
      "step": 1000
    },
    {
      "epoch": 0.03007337904486948,
      "grad_norm": 0.21168646216392517,
      "learning_rate": 2.9097798628653917e-05,
      "loss": 0.0235,
      "step": 1500
    },
    {
      "epoch": 0.04009783872649264,
      "grad_norm": 0.15510809421539307,
      "learning_rate": 2.879706483820522e-05,
      "loss": 0.0225,
      "step": 2000
    },
    {
      "epoch": 0.0501222984081158,
      "grad_norm": 0.2416733056306839,
      "learning_rate": 2.849633104775653e-05,
      "loss": 0.0221,
      "step": 2500
    },
    {
      "epoch": 0.06014675808973896,
      "grad_norm": 0.19131343066692352,
      "learning_rate": 2.819559725730783e-05,
      "loss": 0.021,
      "step": 3000
    },
    {
      "epoch": 0.07017121777136212,
      "grad_norm": 0.14675654470920563,
      "learning_rate": 2.7894863466859138e-05,
      "loss": 0.0209,
      "step": 3500
    },
    {
      "epoch": 0.08019567745298528,
      "grad_norm": 0.1758842021226883,
      "learning_rate": 2.7594129676410442e-05,
      "loss": 0.0205,
      "step": 4000
    },
    {
      "epoch": 0.09022013713460844,
      "grad_norm": 0.14844126999378204,
      "learning_rate": 2.729339588596175e-05,
      "loss": 0.0203,
      "step": 4500
    },
    {
      "epoch": 0.1002445968162316,
      "grad_norm": 0.25966688990592957,
      "learning_rate": 2.699266209551305e-05,
      "loss": 0.02,
      "step": 5000
    },
    {
      "epoch": 0.11026905649785476,
      "grad_norm": 0.15259282290935516,
      "learning_rate": 2.6691928305064358e-05,
      "loss": 0.0201,
      "step": 5500
    },
    {
      "epoch": 0.12029351617947792,
      "grad_norm": 0.2339366376399994,
      "learning_rate": 2.6391194514615663e-05,
      "loss": 0.0197,
      "step": 6000
    },
    {
      "epoch": 0.13031797586110108,
      "grad_norm": 0.19134366512298584,
      "learning_rate": 2.609046072416697e-05,
      "loss": 0.0195,
      "step": 6500
    },
    {
      "epoch": 0.14034243554272424,
      "grad_norm": 0.18384341895580292,
      "learning_rate": 2.578972693371827e-05,
      "loss": 0.0195,
      "step": 7000
    },
    {
      "epoch": 0.1503668952243474,
      "grad_norm": 0.12643477320671082,
      "learning_rate": 2.548899314326958e-05,
      "loss": 0.0189,
      "step": 7500
    },
    {
      "epoch": 0.16039135490597056,
      "grad_norm": 0.1328970193862915,
      "learning_rate": 2.5188259352820883e-05,
      "loss": 0.0189,
      "step": 8000
    },
    {
      "epoch": 0.17041581458759372,
      "grad_norm": 0.11257112771272659,
      "learning_rate": 2.488752556237219e-05,
      "loss": 0.0188,
      "step": 8500
    }
  ],
  "logging_steps": 500,
  "max_steps": 49878,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}