{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10610079575596817,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035366931918656055,
      "eval_loss": 4.540555000305176,
      "eval_runtime": 8.8184,
      "eval_samples_per_second": 13.494,
      "eval_steps_per_second": 6.804,
      "step": 1
    },
    {
      "epoch": 0.010610079575596816,
      "grad_norm": 3.1070003509521484,
      "learning_rate": 3e-05,
      "loss": 4.5239,
      "step": 3
    },
    {
      "epoch": 0.021220159151193633,
      "grad_norm": 3.322465419769287,
      "learning_rate": 6e-05,
      "loss": 4.4687,
      "step": 6
    },
    {
      "epoch": 0.028293545534924844,
      "eval_loss": 4.284606456756592,
      "eval_runtime": 8.5088,
      "eval_samples_per_second": 13.986,
      "eval_steps_per_second": 7.052,
      "step": 8
    },
    {
      "epoch": 0.03183023872679045,
      "grad_norm": 2.4278759956359863,
      "learning_rate": 9e-05,
      "loss": 4.1655,
      "step": 9
    },
    {
      "epoch": 0.042440318302387266,
      "grad_norm": 2.5720601081848145,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.069,
      "step": 12
    },
    {
      "epoch": 0.05305039787798409,
      "grad_norm": 2.05781626701355,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.6597,
      "step": 15
    },
    {
      "epoch": 0.05658709106984969,
      "eval_loss": 3.3761134147644043,
      "eval_runtime": 8.564,
      "eval_samples_per_second": 13.895,
      "eval_steps_per_second": 7.006,
      "step": 16
    },
    {
      "epoch": 0.0636604774535809,
      "grad_norm": 2.680410385131836,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.3868,
      "step": 18
    },
    {
      "epoch": 0.07427055702917772,
      "grad_norm": 2.5410356521606445,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 3.2253,
      "step": 21
    },
    {
      "epoch": 0.08488063660477453,
      "grad_norm": 2.174226760864258,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.8453,
      "step": 24
    },
    {
      "epoch": 0.08488063660477453,
      "eval_loss": 2.9847254753112793,
      "eval_runtime": 8.576,
      "eval_samples_per_second": 13.876,
      "eval_steps_per_second": 6.996,
      "step": 24
    },
    {
      "epoch": 0.09549071618037135,
      "grad_norm": 2.7939352989196777,
      "learning_rate": 5.449673790581611e-06,
      "loss": 3.0492,
      "step": 27
    },
    {
      "epoch": 0.10610079575596817,
      "grad_norm": 2.3326683044433594,
      "learning_rate": 0.0,
      "loss": 2.8804,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4135709237575680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}