{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001886080724254998,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001886080724254998,
      "grad_norm": 0.7263877391815186,
      "learning_rate": 2e-05,
      "loss": 1.1411,
      "step": 1
    },
    {
      "epoch": 0.0001886080724254998,
      "eval_loss": 1.2055432796478271,
      "eval_runtime": 225.574,
      "eval_samples_per_second": 9.899,
      "eval_steps_per_second": 4.952,
      "step": 1
    },
    {
      "epoch": 0.0003772161448509996,
      "grad_norm": 0.6655610799789429,
      "learning_rate": 4e-05,
      "loss": 1.2033,
      "step": 2
    },
    {
      "epoch": 0.0005658242172764995,
      "grad_norm": 0.7066185474395752,
      "learning_rate": 6e-05,
      "loss": 1.2572,
      "step": 3
    },
    {
      "epoch": 0.0005658242172764995,
      "eval_loss": 1.2023361921310425,
      "eval_runtime": 223.6374,
      "eval_samples_per_second": 9.985,
      "eval_steps_per_second": 4.995,
      "step": 3
    },
    {
      "epoch": 0.0007544322897019992,
      "grad_norm": 0.6481005549430847,
      "learning_rate": 8e-05,
      "loss": 1.0235,
      "step": 4
    },
    {
      "epoch": 0.000943040362127499,
      "grad_norm": 0.8814029693603516,
      "learning_rate": 0.0001,
      "loss": 1.3158,
      "step": 5
    },
    {
      "epoch": 0.001131648434552999,
      "grad_norm": 0.7279743552207947,
      "learning_rate": 0.00012,
      "loss": 0.9004,
      "step": 6
    },
    {
      "epoch": 0.001131648434552999,
      "eval_loss": 1.1496310234069824,
      "eval_runtime": 223.5947,
      "eval_samples_per_second": 9.987,
      "eval_steps_per_second": 4.996,
      "step": 6
    },
    {
      "epoch": 0.0013202565069784986,
      "grad_norm": 1.123470664024353,
      "learning_rate": 0.00014,
      "loss": 1.0863,
      "step": 7
    },
    {
      "epoch": 0.0015088645794039985,
      "grad_norm": 1.2135413885116577,
      "learning_rate": 0.00016,
      "loss": 1.22,
      "step": 8
    },
    {
      "epoch": 0.0016974726518294984,
      "grad_norm": 0.9456623196601868,
      "learning_rate": 0.00018,
      "loss": 1.0114,
      "step": 9
    },
    {
      "epoch": 0.0016974726518294984,
      "eval_loss": 0.9456074833869934,
      "eval_runtime": 223.493,
      "eval_samples_per_second": 9.991,
      "eval_steps_per_second": 4.998,
      "step": 9
    },
    {
      "epoch": 0.001886080724254998,
      "grad_norm": 1.0494065284729004,
      "learning_rate": 0.0002,
      "loss": 0.9685,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}