{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 134,
  "global_step": 367,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027247956403269754,
      "eval_loss": 3.203904390335083,
      "eval_runtime": 4.2695,
      "eval_samples_per_second": 72.375,
      "eval_steps_per_second": 18.269,
      "step": 1
    },
    {
      "epoch": 0.1362397820163488,
      "grad_norm": 0.7537987232208252,
      "learning_rate": 0.0004,
      "loss": 1.3941,
      "step": 50
    },
    {
      "epoch": 0.2724795640326976,
      "grad_norm": 0.5926509499549866,
      "learning_rate": 0.0004,
      "loss": 0.8495,
      "step": 100
    },
    {
      "epoch": 0.3651226158038147,
      "eval_loss": 0.6168258190155029,
      "eval_runtime": 4.2281,
      "eval_samples_per_second": 73.082,
      "eval_steps_per_second": 18.448,
      "step": 134
    },
    {
      "epoch": 0.4087193460490463,
      "grad_norm": 0.7156445384025574,
      "learning_rate": 0.0004,
      "loss": 0.6471,
      "step": 150
    },
    {
      "epoch": 0.5449591280653951,
      "grad_norm": 0.9673421382904053,
      "learning_rate": 0.0004,
      "loss": 0.5422,
      "step": 200
    },
    {
      "epoch": 0.6811989100817438,
      "grad_norm": 0.6035718321800232,
      "learning_rate": 0.0004,
      "loss": 0.4256,
      "step": 250
    },
    {
      "epoch": 0.7302452316076294,
      "eval_loss": 0.4029657542705536,
      "eval_runtime": 4.2417,
      "eval_samples_per_second": 72.848,
      "eval_steps_per_second": 18.389,
      "step": 268
    },
    {
      "epoch": 0.8174386920980926,
      "grad_norm": 0.5255013704299927,
      "learning_rate": 0.0004,
      "loss": 0.3641,
      "step": 300
    },
    {
      "epoch": 0.9536784741144414,
      "grad_norm": 0.41406139731407166,
      "learning_rate": 0.0004,
      "loss": 0.2957,
      "step": 350
    }
  ],
  "logging_steps": 50,
  "max_steps": 400,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.189318078660608e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}