trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 6864,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07284382284382285,
      "grad_norm": 3.079172372817993,
      "learning_rate": 1.8543123543123545e-05,
      "loss": 2.2282,
      "step": 500
    },
    {
      "epoch": 0.1456876456876457,
      "grad_norm": 2.744220018386841,
      "learning_rate": 1.7086247086247088e-05,
      "loss": 1.8712,
      "step": 1000
    },
    {
      "epoch": 0.21853146853146854,
      "grad_norm": 3.1921932697296143,
      "learning_rate": 1.562937062937063e-05,
      "loss": 1.7247,
      "step": 1500
    },
    {
      "epoch": 0.2913752913752914,
      "grad_norm": 2.575843334197998,
      "learning_rate": 1.4172494172494174e-05,
      "loss": 1.632,
      "step": 2000
    },
    {
      "epoch": 0.36421911421911424,
      "grad_norm": 2.898587703704834,
      "learning_rate": 1.2715617715617716e-05,
      "loss": 1.5467,
      "step": 2500
    },
    {
      "epoch": 0.4370629370629371,
      "grad_norm": 2.6611907482147217,
      "learning_rate": 1.1258741258741259e-05,
      "loss": 1.5052,
      "step": 3000
    },
    {
      "epoch": 0.5099067599067599,
      "grad_norm": 2.7068097591400146,
      "learning_rate": 9.801864801864802e-06,
      "loss": 1.4542,
      "step": 3500
    },
    {
      "epoch": 0.5827505827505828,
      "grad_norm": 2.4694888591766357,
      "learning_rate": 8.344988344988347e-06,
      "loss": 1.4166,
      "step": 4000
    },
    {
      "epoch": 0.6555944055944056,
      "grad_norm": 2.4586915969848633,
      "learning_rate": 6.888111888111889e-06,
      "loss": 1.3813,
      "step": 4500
    },
    {
      "epoch": 0.7284382284382285,
      "grad_norm": 2.5161385536193848,
      "learning_rate": 5.431235431235432e-06,
      "loss": 1.3543,
      "step": 5000
    },
    {
      "epoch": 0.8012820512820513,
      "grad_norm": 2.7101500034332275,
      "learning_rate": 3.974358974358974e-06,
      "loss": 1.328,
      "step": 5500
    },
    {
      "epoch": 0.8741258741258742,
      "grad_norm": 3.201040506362915,
      "learning_rate": 2.517482517482518e-06,
      "loss": 1.3119,
      "step": 6000
    },
    {
      "epoch": 0.946969696969697,
      "grad_norm": 2.8589653968811035,
      "learning_rate": 1.0606060606060608e-06,
      "loss": 1.3049,
      "step": 6500
    }
  ],
  "logging_steps": 500,
  "max_steps": 6864,
  "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": 4.217315920596173e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}