{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5111821086261981,
      "grad_norm": 3.8581639963400063,
      "learning_rate": 9.644883599083959e-06,
      "loss": 2.5926246643066406,
      "mean_token_accuracy": 0.571833749115467,
      "num_tokens": 85419.0,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.773457138818656,
      "learning_rate": 8.025871075968828e-06,
      "loss": 1.4052116394042968,
      "mean_token_accuracy": 0.6838907081317278,
      "num_tokens": 166976.0,
      "step": 20
    },
    {
      "epoch": 1.511182108626198,
      "grad_norm": 2.8783747913766073,
      "learning_rate": 5.540595092119709e-06,
      "loss": 0.9882570266723633,
      "mean_token_accuracy": 0.7604365691542625,
      "num_tokens": 252778.0,
      "step": 30
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.989038140921467,
      "learning_rate": 2.9005544921986774e-06,
      "loss": 0.9068281173706054,
      "mean_token_accuracy": 0.7778837034125733,
      "num_tokens": 333952.0,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.3071309911097344e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}