trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 188.44981384277344,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 9.2983,
      "step": 10
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 83.63673400878906,
      "learning_rate": 9.090909090909091e-06,
      "loss": 5.2395,
      "step": 20
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 48.23883819580078,
      "learning_rate": 9.595959595959597e-06,
      "loss": 1.8746,
      "step": 30
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 38.73075866699219,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.3606,
      "step": 40
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 24.69623565673828,
      "learning_rate": 8.585858585858587e-06,
      "loss": 0.8711,
      "step": 50
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 21.219209671020508,
      "learning_rate": 8.08080808080808e-06,
      "loss": 0.6953,
      "step": 60
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 22.02012062072754,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.6719,
      "step": 70
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 25.328935623168945,
      "learning_rate": 7.070707070707071e-06,
      "loss": 0.5414,
      "step": 80
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 11.913020133972168,
      "learning_rate": 6.565656565656566e-06,
      "loss": 0.6012,
      "step": 90
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 15.604564666748047,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.4448,
      "step": 100
    },
    {
      "epoch": 10.0,
      "grad_norm": 10.70217514038086,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.4277,
      "step": 110
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 14.791255950927734,
      "learning_rate": 5.0505050505050515e-06,
      "loss": 0.3909,
      "step": 120
    },
    {
      "epoch": 11.818181818181818,
      "grad_norm": 15.777950286865234,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.316,
      "step": 130
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 12.46717643737793,
      "learning_rate": 4.04040404040404e-06,
      "loss": 0.3042,
      "step": 140
    },
    {
      "epoch": 13.636363636363637,
      "grad_norm": 12.875164985656738,
      "learning_rate": 3.5353535353535356e-06,
      "loss": 0.3085,
      "step": 150
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 10.16179084777832,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.2959,
      "step": 160
    }
  ],
  "logging_steps": 10,
  "max_steps": 220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 64,
  "trial_name": null,
  "trial_params": null
}