{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006680896977228162,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3361793954456326e-05,
      "eval_loss": 2.251216411590576,
      "eval_runtime": 964.0542,
      "eval_samples_per_second": 32.687,
      "eval_steps_per_second": 16.343,
      "step": 1
    },
    {
      "epoch": 6.680896977228163e-05,
      "grad_norm": 16.5920467376709,
      "learning_rate": 5e-05,
      "loss": 2.0823,
      "step": 5
    },
    {
      "epoch": 0.00013361793954456326,
      "grad_norm": 9.915910720825195,
      "learning_rate": 0.0001,
      "loss": 1.7611,
      "step": 10
    },
    {
      "epoch": 0.00013361793954456326,
      "eval_loss": 1.591361165046692,
      "eval_runtime": 978.1758,
      "eval_samples_per_second": 32.215,
      "eval_steps_per_second": 16.108,
      "step": 10
    },
    {
      "epoch": 0.00020042690931684488,
      "grad_norm": 10.010727882385254,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2803,
      "step": 15
    },
    {
      "epoch": 0.0002672358790891265,
      "grad_norm": 8.734306335449219,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8639,
      "step": 20
    },
    {
      "epoch": 0.0002672358790891265,
      "eval_loss": 0.7700777053833008,
      "eval_runtime": 987.7208,
      "eval_samples_per_second": 31.904,
      "eval_steps_per_second": 15.952,
      "step": 20
    },
    {
      "epoch": 0.0003340448488614081,
      "grad_norm": 2.2955048084259033,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7105,
      "step": 25
    },
    {
      "epoch": 0.00040085381863368976,
      "grad_norm": 2.6861093044281006,
      "learning_rate": 5e-05,
      "loss": 0.5545,
      "step": 30
    },
    {
      "epoch": 0.00040085381863368976,
      "eval_loss": 0.5168505907058716,
      "eval_runtime": 985.8541,
      "eval_samples_per_second": 31.964,
      "eval_steps_per_second": 15.982,
      "step": 30
    },
    {
      "epoch": 0.0004676627884059714,
      "grad_norm": 2.0121054649353027,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.3929,
      "step": 35
    },
    {
      "epoch": 0.000534471758178253,
      "grad_norm": 2.400435447692871,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5017,
      "step": 40
    },
    {
      "epoch": 0.000534471758178253,
      "eval_loss": 0.4598824679851532,
      "eval_runtime": 981.0301,
      "eval_samples_per_second": 32.121,
      "eval_steps_per_second": 16.061,
      "step": 40
    },
    {
      "epoch": 0.0006012807279505346,
      "grad_norm": 2.469871997833252,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.4224,
      "step": 45
    },
    {
      "epoch": 0.0006680896977228162,
      "grad_norm": 2.691551446914673,
      "learning_rate": 0.0,
      "loss": 0.4594,
      "step": 50
    },
    {
      "epoch": 0.0006680896977228162,
      "eval_loss": 0.4507746994495392,
      "eval_runtime": 981.9631,
      "eval_samples_per_second": 32.091,
      "eval_steps_per_second": 16.045,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}