trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11026905649785476,
  "eval_steps": 500,
  "global_step": 5500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01002445968162316,
      "grad_norm": 0.1908789426088333,
      "learning_rate": 2.969926620955131e-05,
      "loss": 0.0305,
      "step": 500
    },
    {
      "epoch": 0.02004891936324632,
      "grad_norm": 0.2333366870880127,
      "learning_rate": 2.939853241910261e-05,
      "loss": 0.027,
      "step": 1000
    },
    {
      "epoch": 0.03007337904486948,
      "grad_norm": 0.18207737803459167,
      "learning_rate": 2.9097798628653917e-05,
      "loss": 0.026,
      "step": 1500
    },
    {
      "epoch": 0.04009783872649264,
      "grad_norm": 0.13153837621212006,
      "learning_rate": 2.879706483820522e-05,
      "loss": 0.0253,
      "step": 2000
    },
    {
      "epoch": 0.0501222984081158,
      "grad_norm": 0.20580655336380005,
      "learning_rate": 2.849633104775653e-05,
      "loss": 0.0249,
      "step": 2500
    },
    {
      "epoch": 0.06014675808973896,
      "grad_norm": 0.16466622054576874,
      "learning_rate": 2.8196198724888727e-05,
      "loss": 0.0239,
      "step": 3000
    },
    {
      "epoch": 0.07017121777136212,
      "grad_norm": 0.1590748131275177,
      "learning_rate": 2.7895464934440035e-05,
      "loss": 0.0239,
      "step": 3500
    },
    {
      "epoch": 0.08019567745298528,
      "grad_norm": 0.14150911569595337,
      "learning_rate": 2.759473114399134e-05,
      "loss": 0.0236,
      "step": 4000
    },
    {
      "epoch": 0.09022013713460844,
      "grad_norm": 0.09914161264896393,
      "learning_rate": 2.7293997353542647e-05,
      "loss": 0.0236,
      "step": 4500
    },
    {
      "epoch": 0.1002445968162316,
      "grad_norm": 0.16175945103168488,
      "learning_rate": 2.6993263563093947e-05,
      "loss": 0.0232,
      "step": 5000
    },
    {
      "epoch": 0.11026905649785476,
      "grad_norm": 0.14557033777236938,
      "learning_rate": 2.6692529772645255e-05,
      "loss": 0.0229,
      "step": 5500
    }
  ],
  "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
}