{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22857142857142856,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004571428571428572,
      "eval_loss": 2.6391401290893555,
      "eval_runtime": 16.3106,
      "eval_samples_per_second": 5.702,
      "eval_steps_per_second": 2.882,
      "step": 1
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.6253376007080078,
      "learning_rate": 5e-05,
      "loss": 2.6482,
      "step": 5
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.686288058757782,
      "learning_rate": 0.0001,
      "loss": 2.7664,
      "step": 10
    },
    {
      "epoch": 0.045714285714285714,
      "eval_loss": 2.545773983001709,
      "eval_runtime": 17.3817,
      "eval_samples_per_second": 5.35,
      "eval_steps_per_second": 2.704,
      "step": 10
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.8521817922592163,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.4172,
      "step": 15
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.47453853487968445,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.486,
      "step": 20
    },
    {
      "epoch": 0.09142857142857143,
      "eval_loss": 2.4307074546813965,
      "eval_runtime": 17.8847,
      "eval_samples_per_second": 5.2,
      "eval_steps_per_second": 2.628,
      "step": 20
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.7494879961013794,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.5017,
      "step": 25
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.7377310991287231,
      "learning_rate": 5e-05,
      "loss": 2.4914,
      "step": 30
    },
    {
      "epoch": 0.13714285714285715,
      "eval_loss": 2.356546640396118,
      "eval_runtime": 18.0377,
      "eval_samples_per_second": 5.156,
      "eval_steps_per_second": 2.606,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.7005239725112915,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.2993,
      "step": 35
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.5908234119415283,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3373,
      "step": 40
    },
    {
      "epoch": 0.18285714285714286,
      "eval_loss": 2.322948455810547,
      "eval_runtime": 18.0824,
      "eval_samples_per_second": 5.143,
      "eval_steps_per_second": 2.599,
      "step": 40
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.6909214854240417,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.4386,
      "step": 45
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.6680397391319275,
      "learning_rate": 0.0,
      "loss": 2.3495,
      "step": 50
    },
    {
      "epoch": 0.22857142857142856,
      "eval_loss": 2.3178212642669678,
      "eval_runtime": 18.1382,
      "eval_samples_per_second": 5.127,
      "eval_steps_per_second": 2.591,
      "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": 1.84956424814592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}