{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016072002571520413,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003214400514304082,
      "eval_loss": 2.7202465534210205,
      "eval_runtime": 128.7961,
      "eval_samples_per_second": 10.171,
      "eval_steps_per_second": 5.086,
      "step": 1
    },
    {
      "epoch": 0.0016072002571520412,
      "grad_norm": 3.4862313270568848,
      "learning_rate": 5e-05,
      "loss": 10.7866,
      "step": 5
    },
    {
      "epoch": 0.0032144005143040825,
      "grad_norm": 13.840675354003906,
      "learning_rate": 0.0001,
      "loss": 10.8068,
      "step": 10
    },
    {
      "epoch": 0.0032144005143040825,
      "eval_loss": 2.556215286254883,
      "eval_runtime": 129.2338,
      "eval_samples_per_second": 10.137,
      "eval_steps_per_second": 5.068,
      "step": 10
    },
    {
      "epoch": 0.0048216007714561235,
      "grad_norm": 3.8508975505828857,
      "learning_rate": 9.619397662556435e-05,
      "loss": 9.6739,
      "step": 15
    },
    {
      "epoch": 0.006428801028608165,
      "grad_norm": 9.919121742248535,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.3174,
      "step": 20
    },
    {
      "epoch": 0.006428801028608165,
      "eval_loss": 2.0805015563964844,
      "eval_runtime": 129.3236,
      "eval_samples_per_second": 10.13,
      "eval_steps_per_second": 5.065,
      "step": 20
    },
    {
      "epoch": 0.008036001285760206,
      "grad_norm": 5.0153656005859375,
      "learning_rate": 6.91341716182545e-05,
      "loss": 7.8695,
      "step": 25
    },
    {
      "epoch": 0.009643201542912247,
      "grad_norm": 3.4098281860351562,
      "learning_rate": 5e-05,
      "loss": 7.674,
      "step": 30
    },
    {
      "epoch": 0.009643201542912247,
      "eval_loss": 1.9491528272628784,
      "eval_runtime": 129.2259,
      "eval_samples_per_second": 10.137,
      "eval_steps_per_second": 5.069,
      "step": 30
    },
    {
      "epoch": 0.011250401800064288,
      "grad_norm": 3.9341318607330322,
      "learning_rate": 3.086582838174551e-05,
      "loss": 8.0253,
      "step": 35
    },
    {
      "epoch": 0.01285760205721633,
      "grad_norm": 4.0796122550964355,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.0616,
      "step": 40
    },
    {
      "epoch": 0.01285760205721633,
      "eval_loss": 1.911198377609253,
      "eval_runtime": 129.339,
      "eval_samples_per_second": 10.128,
      "eval_steps_per_second": 5.064,
      "step": 40
    },
    {
      "epoch": 0.01446480231436837,
      "grad_norm": 3.8582828044891357,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 7.7004,
      "step": 45
    },
    {
      "epoch": 0.016072002571520413,
      "grad_norm": 3.681159496307373,
      "learning_rate": 0.0,
      "loss": 7.3475,
      "step": 50
    },
    {
      "epoch": 0.016072002571520413,
      "eval_loss": 1.904124140739441,
      "eval_runtime": 129.1904,
      "eval_samples_per_second": 10.14,
      "eval_steps_per_second": 5.07,
      "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": 1.0586869460471808e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}