{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28412874583795783,
  "eval_steps": 8,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03551609322974473,
      "grad_norm": 0.3238994777202606,
      "learning_rate": 5e-05,
      "loss": 1.1629,
      "step": 1
    },
    {
      "epoch": 0.03551609322974473,
      "eval_loss": 1.148727536201477,
      "eval_runtime": 17.5824,
      "eval_samples_per_second": 10.806,
      "eval_steps_per_second": 2.73,
      "step": 1
    },
    {
      "epoch": 0.07103218645948946,
      "grad_norm": 0.30336055159568787,
      "learning_rate": 0.0001,
      "loss": 1.08,
      "step": 2
    },
    {
      "epoch": 0.10654827968923418,
      "grad_norm": 0.32345050573349,
      "learning_rate": 9.966191788709716e-05,
      "loss": 1.1277,
      "step": 3
    },
    {
      "epoch": 0.14206437291897892,
      "grad_norm": 0.2949381172657013,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.0632,
      "step": 4
    },
    {
      "epoch": 0.17758046614872364,
      "grad_norm": 0.28073155879974365,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0568,
      "step": 5
    },
    {
      "epoch": 0.21309655937846836,
      "grad_norm": 0.3517192304134369,
      "learning_rate": 9.468163201617062e-05,
      "loss": 1.0366,
      "step": 6
    },
    {
      "epoch": 0.2486126526082131,
      "grad_norm": 0.37389102578163147,
      "learning_rate": 9.177439057064683e-05,
      "loss": 0.9688,
      "step": 7
    },
    {
      "epoch": 0.28412874583795783,
      "grad_norm": 0.3350629508495331,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.0059,
      "step": 8
    },
    {
      "epoch": 0.28412874583795783,
      "eval_loss": 0.9954966306686401,
      "eval_runtime": 17.632,
      "eval_samples_per_second": 10.776,
      "eval_steps_per_second": 2.722,
      "step": 8
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.899231445914747e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}