{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008150457444424068,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.150457444424068e-05,
      "grad_norm": 2.7867870330810547,
      "learning_rate": 2e-05,
      "loss": 44.5881,
      "step": 1
    },
    {
      "epoch": 8.150457444424068e-05,
      "eval_loss": 11.109837532043457,
      "eval_runtime": 72.8634,
      "eval_samples_per_second": 35.45,
      "eval_steps_per_second": 35.45,
      "step": 1
    },
    {
      "epoch": 0.00016300914888848136,
      "grad_norm": 1.9754440784454346,
      "learning_rate": 4e-05,
      "loss": 44.577,
      "step": 2
    },
    {
      "epoch": 0.00024451372333272203,
      "grad_norm": 2.171830654144287,
      "learning_rate": 6e-05,
      "loss": 44.4605,
      "step": 3
    },
    {
      "epoch": 0.00024451372333272203,
      "eval_loss": 11.109298706054688,
      "eval_runtime": 72.7695,
      "eval_samples_per_second": 35.496,
      "eval_steps_per_second": 35.496,
      "step": 3
    },
    {
      "epoch": 0.0003260182977769627,
      "grad_norm": 1.6170740127563477,
      "learning_rate": 8e-05,
      "loss": 44.4044,
      "step": 4
    },
    {
      "epoch": 0.0004075228722212034,
      "grad_norm": 1.9462393522262573,
      "learning_rate": 0.0001,
      "loss": 44.4228,
      "step": 5
    },
    {
      "epoch": 0.0004890274466654441,
      "grad_norm": 2.87850284576416,
      "learning_rate": 0.00012,
      "loss": 44.4399,
      "step": 6
    },
    {
      "epoch": 0.0004890274466654441,
      "eval_loss": 11.106473922729492,
      "eval_runtime": 72.9951,
      "eval_samples_per_second": 35.386,
      "eval_steps_per_second": 35.386,
      "step": 6
    },
    {
      "epoch": 0.0005705320211096848,
      "grad_norm": 2.844712495803833,
      "learning_rate": 0.00014,
      "loss": 44.4716,
      "step": 7
    },
    {
      "epoch": 0.0006520365955539254,
      "grad_norm": 2.5091469287872314,
      "learning_rate": 0.00016,
      "loss": 44.2388,
      "step": 8
    },
    {
      "epoch": 0.0007335411699981661,
      "grad_norm": 1.7652978897094727,
      "learning_rate": 0.00018,
      "loss": 44.4253,
      "step": 9
    },
    {
      "epoch": 0.0007335411699981661,
      "eval_loss": 11.101712226867676,
      "eval_runtime": 73.0556,
      "eval_samples_per_second": 35.357,
      "eval_steps_per_second": 35.357,
      "step": 9
    },
    {
      "epoch": 0.0008150457444424068,
      "grad_norm": 2.4019575119018555,
      "learning_rate": 0.0002,
      "loss": 44.4778,
      "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": 415991070720.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}