{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005240482729082159,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0155702804162153e-05,
      "eval_loss": 1.8410059213638306,
      "eval_runtime": 1886.297,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 5.537,
      "step": 1
    },
    {
      "epoch": 0.00010077851402081077,
      "grad_norm": 1.935125470161438,
      "learning_rate": 5e-05,
      "loss": 1.8486,
      "step": 5
    },
    {
      "epoch": 0.00020155702804162154,
      "grad_norm": 1.3043996095657349,
      "learning_rate": 0.0001,
      "loss": 1.658,
      "step": 10
    },
    {
      "epoch": 0.00020155702804162154,
      "eval_loss": 1.4670926332473755,
      "eval_runtime": 1890.2781,
      "eval_samples_per_second": 11.051,
      "eval_steps_per_second": 5.526,
      "step": 10
    },
    {
      "epoch": 0.0003023355420624323,
      "grad_norm": 1.296493411064148,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1661,
      "step": 15
    },
    {
      "epoch": 0.0004031140560832431,
      "grad_norm": 0.7659422755241394,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3867,
      "step": 20
    },
    {
      "epoch": 0.0004031140560832431,
      "eval_loss": 1.1846641302108765,
      "eval_runtime": 1888.6218,
      "eval_samples_per_second": 11.061,
      "eval_steps_per_second": 5.53,
      "step": 20
    },
    {
      "epoch": 0.0005038925701040538,
      "grad_norm": 1.5011175870895386,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3181,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6982105036750848.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}