{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.033426183844011144,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003714020427112349,
      "grad_norm": 0.5405333042144775,
      "learning_rate": 2e-05,
      "loss": 2.7717,
      "step": 1
    },
    {
      "epoch": 0.003714020427112349,
      "eval_loss": 2.7589731216430664,
      "eval_runtime": 7.8472,
      "eval_samples_per_second": 14.528,
      "eval_steps_per_second": 7.264,
      "step": 1
    },
    {
      "epoch": 0.007428040854224698,
      "grad_norm": 0.5611510276794434,
      "learning_rate": 4e-05,
      "loss": 2.8894,
      "step": 2
    },
    {
      "epoch": 0.011142061281337047,
      "grad_norm": 0.5387593507766724,
      "learning_rate": 6e-05,
      "loss": 2.8945,
      "step": 3
    },
    {
      "epoch": 0.011142061281337047,
      "eval_loss": 2.75407338142395,
      "eval_runtime": 6.482,
      "eval_samples_per_second": 17.587,
      "eval_steps_per_second": 8.794,
      "step": 3
    },
    {
      "epoch": 0.014856081708449397,
      "grad_norm": 0.5385937094688416,
      "learning_rate": 8e-05,
      "loss": 2.8426,
      "step": 4
    },
    {
      "epoch": 0.018570102135561744,
      "grad_norm": 0.5805826783180237,
      "learning_rate": 0.0001,
      "loss": 3.0112,
      "step": 5
    },
    {
      "epoch": 0.022284122562674095,
      "grad_norm": 0.6287373304367065,
      "learning_rate": 0.00012,
      "loss": 2.7749,
      "step": 6
    },
    {
      "epoch": 0.022284122562674095,
      "eval_loss": 2.6834802627563477,
      "eval_runtime": 6.4862,
      "eval_samples_per_second": 17.576,
      "eval_steps_per_second": 8.788,
      "step": 6
    },
    {
      "epoch": 0.025998142989786442,
      "grad_norm": 0.4952622950077057,
      "learning_rate": 0.00014,
      "loss": 2.658,
      "step": 7
    },
    {
      "epoch": 0.029712163416898793,
      "grad_norm": 0.5481176972389221,
      "learning_rate": 0.00016,
      "loss": 2.612,
      "step": 8
    },
    {
      "epoch": 0.033426183844011144,
      "grad_norm": 1.0886715650558472,
      "learning_rate": 0.00018,
      "loss": 2.7356,
      "step": 9
    },
    {
      "epoch": 0.033426183844011144,
      "eval_loss": 2.6656382083892822,
      "eval_runtime": 6.4924,
      "eval_samples_per_second": 17.559,
      "eval_steps_per_second": 8.779,
      "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": 3329215646662656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}