{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 0.7079986148748518,
      "learning_rate": 9.745834992450688e-06,
      "loss": 0.3882425308227539,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6250265786305943,
      "learning_rate": 8.64839582897015e-06,
      "loss": 0.2884632110595703,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.7014561886986339,
      "learning_rate": 6.878381276221777e-06,
      "loss": 0.24055294036865235,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6683347354350464,
      "learning_rate": 4.762090420881289e-06,
      "loss": 0.1965186309814453,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7284867299833838,
      "learning_rate": 2.689657780298019e-06,
      "loss": 0.19071041107177733,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.8642127471212965,
      "learning_rate": 1.0431326866479457e-06,
      "loss": 0.12675453186035157,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.71206320276362,
      "learning_rate": 1.2604916083075236e-07,
      "loss": 0.12834136962890624,
      "step": 350
    }
  ],
  "logging_steps": 50,
  "max_steps": 375,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7801590251520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}