trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 6424,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6226650062266501,
      "grad_norm": 2.0943491458892822,
      "learning_rate": 0.00019886329318816558,
      "loss": 1.2905,
      "step": 500
    },
    {
      "epoch": 1.2453300124533002,
      "grad_norm": 1.3522595167160034,
      "learning_rate": 0.00019197713211971837,
      "loss": 0.9564,
      "step": 1000
    },
    {
      "epoch": 1.86799501867995,
      "grad_norm": 1.6422098875045776,
      "learning_rate": 0.00017926358149064194,
      "loss": 0.8082,
      "step": 1500
    },
    {
      "epoch": 2.4906600249066004,
      "grad_norm": 1.4689579010009766,
      "learning_rate": 0.00016152813295420922,
      "loss": 0.6228,
      "step": 2000
    },
    {
      "epoch": 3.1133250311332503,
      "grad_norm": 2.0464258193969727,
      "learning_rate": 0.000139894450243703,
      "loss": 0.5506,
      "step": 2500
    },
    {
      "epoch": 3.7359900373599,
      "grad_norm": 1.3183234930038452,
      "learning_rate": 0.0001157331772776689,
      "loss": 0.3943,
      "step": 3000
    },
    {
      "epoch": 4.35865504358655,
      "grad_norm": 1.1212505102157593,
      "learning_rate": 9.057509835660592e-05,
      "loss": 0.3245,
      "step": 3500
    },
    {
      "epoch": 4.981320049813201,
      "grad_norm": 1.7740994691848755,
      "learning_rate": 6.601415235522544e-05,
      "loss": 0.2671,
      "step": 4000
    },
    {
      "epoch": 5.603985056039851,
      "grad_norm": 1.0328716039657593,
      "learning_rate": 4.360644563419686e-05,
      "loss": 0.192,
      "step": 4500
    },
    {
      "epoch": 6.226650062266501,
      "grad_norm": 0.7897807955741882,
      "learning_rate": 2.4771661904182066e-05,
      "loss": 0.1778,
      "step": 5000
    },
    {
      "epoch": 6.8493150684931505,
      "grad_norm": 0.8206276297569275,
      "learning_rate": 1.0703115411401943e-05,
      "loss": 0.1591,
      "step": 5500
    },
    {
      "epoch": 7.4719800747198,
      "grad_norm": 0.5427886843681335,
      "learning_rate": 2.292146199581047e-06,
      "loss": 0.1427,
      "step": 6000
    }
  ],
  "logging_steps": 500,
  "max_steps": 6424,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 4739003604203904.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}