{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 5026,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19896538002387584,
      "grad_norm": 0.22902533411979675,
      "learning_rate": 5e-05,
      "loss": 3.7966,
      "step": 500
    },
    {
      "epoch": 0.3979307600477517,
      "grad_norm": 0.22708623111248016,
      "learning_rate": 4.447635881573133e-05,
      "loss": 1.4108,
      "step": 1000
    },
    {
      "epoch": 0.5968961400716275,
      "grad_norm": 0.20095278322696686,
      "learning_rate": 3.895271763146266e-05,
      "loss": 1.365,
      "step": 1500
    },
    {
      "epoch": 0.7958615200955034,
      "grad_norm": 0.1303737759590149,
      "learning_rate": 3.342907644719399e-05,
      "loss": 1.3683,
      "step": 2000
    },
    {
      "epoch": 0.9948269001193792,
      "grad_norm": 0.21030685305595398,
      "learning_rate": 2.7905435262925323e-05,
      "loss": 1.3898,
      "step": 2500
    },
    {
      "epoch": 1.193792280143255,
      "grad_norm": 0.18989521265029907,
      "learning_rate": 2.2381794078656652e-05,
      "loss": 1.3441,
      "step": 3000
    },
    {
      "epoch": 1.392757660167131,
      "grad_norm": 0.19548365473747253,
      "learning_rate": 1.6858152894387984e-05,
      "loss": 1.3469,
      "step": 3500
    },
    {
      "epoch": 1.5917230401910067,
      "grad_norm": 0.23873193562030792,
      "learning_rate": 1.133451171011931e-05,
      "loss": 1.3736,
      "step": 4000
    },
    {
      "epoch": 1.7906884202148827,
      "grad_norm": 0.2010679692029953,
      "learning_rate": 5.810870525850641e-06,
      "loss": 1.3847,
      "step": 4500
    },
    {
      "epoch": 1.9896538002387585,
      "grad_norm": 0.19471381604671478,
      "learning_rate": 2.872293415819708e-07,
      "loss": 1.3575,
      "step": 5000
    }
  ],
  "logging_steps": 500,
  "max_steps": 5026,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.88611238559744e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}