trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9961977186311787,
  "eval_steps": 500,
  "global_step": 131,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07604562737642585,
      "grad_norm": 3.9607327619115638,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.0044,
      "step": 10
    },
    {
      "epoch": 0.1520912547528517,
      "grad_norm": 2.414984356209713,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.7328,
      "step": 20
    },
    {
      "epoch": 0.22813688212927757,
      "grad_norm": 1.8311424443701727,
      "learning_rate": 1e-05,
      "loss": 1.5477,
      "step": 30
    },
    {
      "epoch": 0.3041825095057034,
      "grad_norm": 2.7342693836090235,
      "learning_rate": 9.76006553766365e-06,
      "loss": 1.4816,
      "step": 40
    },
    {
      "epoch": 0.38022813688212925,
      "grad_norm": 1.0932759746982914,
      "learning_rate": 9.063289569141251e-06,
      "loss": 1.3696,
      "step": 50
    },
    {
      "epoch": 0.45627376425855515,
      "grad_norm": 0.8027829855103967,
      "learning_rate": 7.97654432138333e-06,
      "loss": 1.295,
      "step": 60
    },
    {
      "epoch": 0.532319391634981,
      "grad_norm": 0.784888378767144,
      "learning_rate": 6.6041288490768385e-06,
      "loss": 1.2598,
      "step": 70
    },
    {
      "epoch": 0.6083650190114068,
      "grad_norm": 1.0684464517481285,
      "learning_rate": 5.077759059601756e-06,
      "loss": 1.2413,
      "step": 80
    },
    {
      "epoch": 0.6844106463878327,
      "grad_norm": 0.7774405522466961,
      "learning_rate": 3.5439264388637407e-06,
      "loss": 1.2327,
      "step": 90
    },
    {
      "epoch": 0.7604562737642585,
      "grad_norm": 0.6695753165424744,
      "learning_rate": 2.149838708931087e-06,
      "loss": 1.2027,
      "step": 100
    },
    {
      "epoch": 0.8365019011406845,
      "grad_norm": 0.6350073566027052,
      "learning_rate": 1.0292917457762325e-06,
      "loss": 1.2002,
      "step": 110
    },
    {
      "epoch": 0.9125475285171103,
      "grad_norm": 2.417352632854064,
      "learning_rate": 2.8982868265005457e-07,
      "loss": 1.1979,
      "step": 120
    },
    {
      "epoch": 0.9885931558935361,
      "grad_norm": 5.195102525743944,
      "learning_rate": 2.4185885400596076e-09,
      "loss": 1.2096,
      "step": 130
    }
  ],
  "logging_steps": 10,
  "max_steps": 131,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 42562454814720.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}