{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0049504950495049506,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004950495049504951,
      "grad_norm": 0.47844815254211426,
      "learning_rate": 2e-05,
      "loss": 2.5697,
      "step": 1
    },
    {
      "epoch": 0.0004950495049504951,
      "eval_loss": 2.622131824493408,
      "eval_runtime": 16.0465,
      "eval_samples_per_second": 53.033,
      "eval_steps_per_second": 26.548,
      "step": 1
    },
    {
      "epoch": 0.0009900990099009901,
      "grad_norm": 0.514812171459198,
      "learning_rate": 4e-05,
      "loss": 2.6019,
      "step": 2
    },
    {
      "epoch": 0.0014851485148514852,
      "grad_norm": 0.9778799414634705,
      "learning_rate": 6e-05,
      "loss": 2.5228,
      "step": 3
    },
    {
      "epoch": 0.0014851485148514852,
      "eval_loss": 2.61960506439209,
      "eval_runtime": 14.776,
      "eval_samples_per_second": 57.594,
      "eval_steps_per_second": 28.831,
      "step": 3
    },
    {
      "epoch": 0.0019801980198019802,
      "grad_norm": 0.7754778265953064,
      "learning_rate": 8e-05,
      "loss": 2.6802,
      "step": 4
    },
    {
      "epoch": 0.0024752475247524753,
      "grad_norm": 0.6502236723899841,
      "learning_rate": 0.0001,
      "loss": 2.361,
      "step": 5
    },
    {
      "epoch": 0.0029702970297029703,
      "grad_norm": 0.8173229098320007,
      "learning_rate": 0.00012,
      "loss": 2.387,
      "step": 6
    },
    {
      "epoch": 0.0029702970297029703,
      "eval_loss": 2.6078779697418213,
      "eval_runtime": 14.9151,
      "eval_samples_per_second": 57.056,
      "eval_steps_per_second": 28.562,
      "step": 6
    },
    {
      "epoch": 0.0034653465346534654,
      "grad_norm": 0.6264777779579163,
      "learning_rate": 0.00014,
      "loss": 2.8017,
      "step": 7
    },
    {
      "epoch": 0.0039603960396039604,
      "grad_norm": 0.6381897330284119,
      "learning_rate": 0.00016,
      "loss": 2.5277,
      "step": 8
    },
    {
      "epoch": 0.004455445544554455,
      "grad_norm": 0.7844493389129639,
      "learning_rate": 0.00018,
      "loss": 2.4812,
      "step": 9
    },
    {
      "epoch": 0.004455445544554455,
      "eval_loss": 2.5712156295776367,
      "eval_runtime": 14.8711,
      "eval_samples_per_second": 57.225,
      "eval_steps_per_second": 28.646,
      "step": 9
    },
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": 0.6121769547462463,
      "learning_rate": 0.0002,
      "loss": 2.5837,
      "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": 326134772269056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}