{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000127712289753643,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2771228975364299e-05,
      "grad_norm": 1.0596935749053955,
      "learning_rate": 2e-05,
      "loss": 3.2321,
      "step": 1
    },
    {
      "epoch": 1.2771228975364299e-05,
      "eval_loss": 3.49228572845459,
      "eval_runtime": 308.7112,
      "eval_samples_per_second": 106.796,
      "eval_steps_per_second": 53.399,
      "step": 1
    },
    {
      "epoch": 2.5542457950728598e-05,
      "grad_norm": 1.0872184038162231,
      "learning_rate": 4e-05,
      "loss": 3.4583,
      "step": 2
    },
    {
      "epoch": 3.8313686926092896e-05,
      "grad_norm": 1.0160207748413086,
      "learning_rate": 6e-05,
      "loss": 3.4287,
      "step": 3
    },
    {
      "epoch": 3.8313686926092896e-05,
      "eval_loss": 3.49009108543396,
      "eval_runtime": 309.7825,
      "eval_samples_per_second": 106.426,
      "eval_steps_per_second": 53.215,
      "step": 3
    },
    {
      "epoch": 5.1084915901457196e-05,
      "grad_norm": 0.9734309315681458,
      "learning_rate": 8e-05,
      "loss": 3.4521,
      "step": 4
    },
    {
      "epoch": 6.38561448768215e-05,
      "grad_norm": 1.1195398569107056,
      "learning_rate": 0.0001,
      "loss": 3.3966,
      "step": 5
    },
    {
      "epoch": 7.662737385218579e-05,
      "grad_norm": 1.0719833374023438,
      "learning_rate": 0.00012,
      "loss": 3.2817,
      "step": 6
    },
    {
      "epoch": 7.662737385218579e-05,
      "eval_loss": 3.4545137882232666,
      "eval_runtime": 310.0065,
      "eval_samples_per_second": 106.349,
      "eval_steps_per_second": 53.176,
      "step": 6
    },
    {
      "epoch": 8.93986028275501e-05,
      "grad_norm": 1.062922477722168,
      "learning_rate": 0.00014,
      "loss": 3.6813,
      "step": 7
    },
    {
      "epoch": 0.00010216983180291439,
      "grad_norm": 1.1093658208847046,
      "learning_rate": 0.00016,
      "loss": 3.5012,
      "step": 8
    },
    {
      "epoch": 0.0001149410607782787,
      "grad_norm": 1.029537558555603,
      "learning_rate": 0.00018,
      "loss": 3.4697,
      "step": 9
    },
    {
      "epoch": 0.0001149410607782787,
      "eval_loss": 3.334758758544922,
      "eval_runtime": 309.3582,
      "eval_samples_per_second": 106.572,
      "eval_steps_per_second": 53.288,
      "step": 9
    },
    {
      "epoch": 0.000127712289753643,
      "grad_norm": 0.981518030166626,
      "learning_rate": 0.0002,
      "loss": 3.4075,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 34292650475520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}