{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004968944099378882,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6563146997929607e-05,
      "eval_loss": 1.8956127166748047,
      "eval_runtime": 1543.395,
      "eval_samples_per_second": 16.471,
      "eval_steps_per_second": 8.236,
      "step": 1
    },
    {
      "epoch": 4.968944099378882e-05,
      "grad_norm": 0.5260406732559204,
      "learning_rate": 6e-05,
      "loss": 1.9781,
      "step": 3
    },
    {
      "epoch": 9.937888198757764e-05,
      "grad_norm": 0.6313697695732117,
      "learning_rate": 0.00012,
      "loss": 1.9471,
      "step": 6
    },
    {
      "epoch": 0.00013250517598343685,
      "eval_loss": 1.696118950843811,
      "eval_runtime": 1541.8413,
      "eval_samples_per_second": 16.487,
      "eval_steps_per_second": 8.244,
      "step": 8
    },
    {
      "epoch": 0.00014906832298136645,
      "grad_norm": 0.3783658742904663,
      "learning_rate": 0.00018,
      "loss": 1.6698,
      "step": 9
    },
    {
      "epoch": 0.00019875776397515528,
      "grad_norm": 0.7311481237411499,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.6247,
      "step": 12
    },
    {
      "epoch": 0.0002484472049689441,
      "grad_norm": 0.39477047324180603,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.6662,
      "step": 15
    },
    {
      "epoch": 0.0002650103519668737,
      "eval_loss": 1.5430463552474976,
      "eval_runtime": 1534.7994,
      "eval_samples_per_second": 16.563,
      "eval_steps_per_second": 8.282,
      "step": 16
    },
    {
      "epoch": 0.0002981366459627329,
      "grad_norm": 0.32923993468284607,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6558,
      "step": 18
    },
    {
      "epoch": 0.00034782608695652176,
      "grad_norm": 0.4157695174217224,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.5317,
      "step": 21
    },
    {
      "epoch": 0.00039751552795031056,
      "grad_norm": 0.3011435270309448,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.4738,
      "step": 24
    },
    {
      "epoch": 0.00039751552795031056,
      "eval_loss": 1.5069102048873901,
      "eval_runtime": 1535.4174,
      "eval_samples_per_second": 16.556,
      "eval_steps_per_second": 8.279,
      "step": 24
    },
    {
      "epoch": 0.00044720496894409936,
      "grad_norm": 0.29339587688446045,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.476,
      "step": 27
    },
    {
      "epoch": 0.0004968944099378882,
      "grad_norm": 0.2849108576774597,
      "learning_rate": 0.0,
      "loss": 1.5091,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4939038012211200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}