{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18450184501845018,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036900369003690036,
      "eval_loss": 11.171310424804688,
      "eval_runtime": 2.1084,
      "eval_samples_per_second": 54.543,
      "eval_steps_per_second": 27.509,
      "step": 1
    },
    {
      "epoch": 0.01845018450184502,
      "grad_norm": 2.670919895172119,
      "learning_rate": 5e-05,
      "loss": 44.6709,
      "step": 5
    },
    {
      "epoch": 0.03690036900369004,
      "grad_norm": 2.698882818222046,
      "learning_rate": 0.0001,
      "loss": 44.6349,
      "step": 10
    },
    {
      "epoch": 0.03690036900369004,
      "eval_loss": 11.152227401733398,
      "eval_runtime": 0.8795,
      "eval_samples_per_second": 130.758,
      "eval_steps_per_second": 65.947,
      "step": 10
    },
    {
      "epoch": 0.055350553505535055,
      "grad_norm": 2.504798650741577,
      "learning_rate": 9.619397662556435e-05,
      "loss": 44.5843,
      "step": 15
    },
    {
      "epoch": 0.07380073800738007,
      "grad_norm": 2.633497714996338,
      "learning_rate": 8.535533905932738e-05,
      "loss": 44.4848,
      "step": 20
    },
    {
      "epoch": 0.07380073800738007,
      "eval_loss": 11.102351188659668,
      "eval_runtime": 0.9003,
      "eval_samples_per_second": 127.733,
      "eval_steps_per_second": 64.422,
      "step": 20
    },
    {
      "epoch": 0.09225092250922509,
      "grad_norm": 2.813123941421509,
      "learning_rate": 6.91341716182545e-05,
      "loss": 44.3679,
      "step": 25
    },
    {
      "epoch": 0.11070110701107011,
      "grad_norm": 2.352640390396118,
      "learning_rate": 5e-05,
      "loss": 44.3003,
      "step": 30
    },
    {
      "epoch": 0.11070110701107011,
      "eval_loss": 11.058656692504883,
      "eval_runtime": 0.9737,
      "eval_samples_per_second": 118.103,
      "eval_steps_per_second": 59.565,
      "step": 30
    },
    {
      "epoch": 0.12915129151291513,
      "grad_norm": 2.5816919803619385,
      "learning_rate": 3.086582838174551e-05,
      "loss": 44.239,
      "step": 35
    },
    {
      "epoch": 0.14760147601476015,
      "grad_norm": 2.871511697769165,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 44.1332,
      "step": 40
    },
    {
      "epoch": 0.14760147601476015,
      "eval_loss": 11.035828590393066,
      "eval_runtime": 0.982,
      "eval_samples_per_second": 117.114,
      "eval_steps_per_second": 59.066,
      "step": 40
    },
    {
      "epoch": 0.16605166051660517,
      "grad_norm": 3.0464413166046143,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 44.1176,
      "step": 45
    },
    {
      "epoch": 0.18450184501845018,
      "grad_norm": 3.0706965923309326,
      "learning_rate": 0.0,
      "loss": 44.1318,
      "step": 50
    },
    {
      "epoch": 0.18450184501845018,
      "eval_loss": 11.03135871887207,
      "eval_runtime": 0.9905,
      "eval_samples_per_second": 116.108,
      "eval_steps_per_second": 58.559,
      "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": 962069004288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}