{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006858841236877703,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.620934707641892e-05,
      "grad_norm": 2.9546027183532715,
      "learning_rate": 2e-05,
      "loss": 7.9647,
      "step": 1
    },
    {
      "epoch": 7.620934707641892e-05,
      "eval_loss": 1.8767974376678467,
      "eval_runtime": 161.2141,
      "eval_samples_per_second": 34.271,
      "eval_steps_per_second": 17.139,
      "step": 1
    },
    {
      "epoch": 0.00015241869415283783,
      "grad_norm": 3.3858532905578613,
      "learning_rate": 4e-05,
      "loss": 7.0786,
      "step": 2
    },
    {
      "epoch": 0.00022862804122925678,
      "grad_norm": 4.023545265197754,
      "learning_rate": 6e-05,
      "loss": 8.385,
      "step": 3
    },
    {
      "epoch": 0.00022862804122925678,
      "eval_loss": 1.868618130683899,
      "eval_runtime": 161.8399,
      "eval_samples_per_second": 34.139,
      "eval_steps_per_second": 17.072,
      "step": 3
    },
    {
      "epoch": 0.00030483738830567567,
      "grad_norm": 3.081524133682251,
      "learning_rate": 8e-05,
      "loss": 6.9845,
      "step": 4
    },
    {
      "epoch": 0.00038104673538209464,
      "grad_norm": 4.906613349914551,
      "learning_rate": 0.0001,
      "loss": 7.008,
      "step": 5
    },
    {
      "epoch": 0.00045725608245851356,
      "grad_norm": 4.26068639755249,
      "learning_rate": 0.00012,
      "loss": 6.8992,
      "step": 6
    },
    {
      "epoch": 0.00045725608245851356,
      "eval_loss": 1.7631769180297852,
      "eval_runtime": 161.4627,
      "eval_samples_per_second": 34.218,
      "eval_steps_per_second": 17.112,
      "step": 6
    },
    {
      "epoch": 0.0005334654295349325,
      "grad_norm": 4.507593631744385,
      "learning_rate": 0.00014,
      "loss": 6.9796,
      "step": 7
    },
    {
      "epoch": 0.0006096747766113513,
      "grad_norm": 3.349161148071289,
      "learning_rate": 0.00016,
      "loss": 6.7286,
      "step": 8
    },
    {
      "epoch": 0.0006858841236877703,
      "grad_norm": 2.6401185989379883,
      "learning_rate": 0.00018,
      "loss": 8.0305,
      "step": 9
    },
    {
      "epoch": 0.0006858841236877703,
      "eval_loss": 1.5174860954284668,
      "eval_runtime": 161.4623,
      "eval_samples_per_second": 34.219,
      "eval_steps_per_second": 17.112,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 872055708844032.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}