{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013067624959163672,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013067624959163672,
      "grad_norm": 1.7657692432403564,
      "learning_rate": 2e-05,
      "loss": 6.7344,
      "step": 1
    },
    {
      "epoch": 0.0013067624959163672,
      "eval_loss": 6.717371940612793,
      "eval_runtime": 16.7474,
      "eval_samples_per_second": 19.287,
      "eval_steps_per_second": 9.673,
      "step": 1
    },
    {
      "epoch": 0.0026135249918327343,
      "grad_norm": 1.6176117658615112,
      "learning_rate": 4e-05,
      "loss": 6.7046,
      "step": 2
    },
    {
      "epoch": 0.003920287487749101,
      "grad_norm": 1.6528016328811646,
      "learning_rate": 6e-05,
      "loss": 5.8803,
      "step": 3
    },
    {
      "epoch": 0.003920287487749101,
      "eval_loss": 6.710137844085693,
      "eval_runtime": 14.7271,
      "eval_samples_per_second": 21.932,
      "eval_steps_per_second": 11.0,
      "step": 3
    },
    {
      "epoch": 0.005227049983665469,
      "grad_norm": 1.8608736991882324,
      "learning_rate": 8e-05,
      "loss": 5.9868,
      "step": 4
    },
    {
      "epoch": 0.006533812479581836,
      "grad_norm": 2.0123531818389893,
      "learning_rate": 0.0001,
      "loss": 4.8973,
      "step": 5
    },
    {
      "epoch": 0.007840574975498203,
      "grad_norm": 2.2245185375213623,
      "learning_rate": 0.00012,
      "loss": 5.5564,
      "step": 6
    },
    {
      "epoch": 0.007840574975498203,
      "eval_loss": 6.524731636047363,
      "eval_runtime": 14.77,
      "eval_samples_per_second": 21.869,
      "eval_steps_per_second": 10.968,
      "step": 6
    },
    {
      "epoch": 0.00914733747141457,
      "grad_norm": 2.8602676391601562,
      "learning_rate": 0.00014,
      "loss": 5.6889,
      "step": 7
    },
    {
      "epoch": 0.010454099967330937,
      "grad_norm": 2.6527276039123535,
      "learning_rate": 0.00016,
      "loss": 5.2183,
      "step": 8
    },
    {
      "epoch": 0.011760862463247305,
      "grad_norm": 2.932201623916626,
      "learning_rate": 0.00018,
      "loss": 4.7739,
      "step": 9
    },
    {
      "epoch": 0.011760862463247305,
      "eval_loss": 5.452193260192871,
      "eval_runtime": 14.8133,
      "eval_samples_per_second": 21.805,
      "eval_steps_per_second": 10.936,
      "step": 9
    },
    {
      "epoch": 0.013067624959163672,
      "grad_norm": 2.4018781185150146,
      "learning_rate": 0.0002,
      "loss": 4.6505,
      "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": 3136744882962432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}