{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.42735042735042733,
  "eval_steps": 300,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.053418803418803416,
      "grad_norm": 1.2336026430130005,
      "learning_rate": 2.3845381526104417e-05,
      "loss": 1.4661,
      "step": 25
    },
    {
      "epoch": 0.10683760683760683,
      "grad_norm": 0.9200632572174072,
      "learning_rate": 2.2590361445783133e-05,
      "loss": 0.418,
      "step": 50
    },
    {
      "epoch": 0.16025641025641027,
      "grad_norm": 0.7277231812477112,
      "learning_rate": 2.1335341365461846e-05,
      "loss": 0.3735,
      "step": 75
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.7124351263046265,
      "learning_rate": 2.0080321285140562e-05,
      "loss": 0.3298,
      "step": 100
    },
    {
      "epoch": 0.2670940170940171,
      "grad_norm": 0.7353916764259338,
      "learning_rate": 1.882530120481928e-05,
      "loss": 0.3257,
      "step": 125
    },
    {
      "epoch": 0.32051282051282054,
      "grad_norm": 0.7286151647567749,
      "learning_rate": 1.7570281124497992e-05,
      "loss": 0.3345,
      "step": 150
    },
    {
      "epoch": 0.37393162393162394,
      "grad_norm": 0.9105963706970215,
      "learning_rate": 1.6315261044176708e-05,
      "loss": 0.3664,
      "step": 175
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.7256978154182434,
      "learning_rate": 1.5060240963855424e-05,
      "loss": 0.3613,
      "step": 200
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2525386115072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}