{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003372169485238328,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.372169485238328e-05,
      "grad_norm": 0.3240683972835541,
      "learning_rate": 2e-05,
      "loss": 2.6964,
      "step": 1
    },
    {
      "epoch": 3.372169485238328e-05,
      "eval_loss": 0.6847627758979797,
      "eval_runtime": 861.2797,
      "eval_samples_per_second": 14.498,
      "eval_steps_per_second": 7.25,
      "step": 1
    },
    {
      "epoch": 6.744338970476656e-05,
      "grad_norm": 0.2931531071662903,
      "learning_rate": 4e-05,
      "loss": 2.5339,
      "step": 2
    },
    {
      "epoch": 0.00010116508455714984,
      "grad_norm": 0.35696616768836975,
      "learning_rate": 6e-05,
      "loss": 2.7371,
      "step": 3
    },
    {
      "epoch": 0.00010116508455714984,
      "eval_loss": 0.6845428347587585,
      "eval_runtime": 862.2133,
      "eval_samples_per_second": 14.482,
      "eval_steps_per_second": 7.242,
      "step": 3
    },
    {
      "epoch": 0.0001348867794095331,
      "grad_norm": 0.3407038152217865,
      "learning_rate": 8e-05,
      "loss": 2.5913,
      "step": 4
    },
    {
      "epoch": 0.0001686084742619164,
      "grad_norm": 0.323496550321579,
      "learning_rate": 0.0001,
      "loss": 2.8172,
      "step": 5
    },
    {
      "epoch": 0.00020233016911429968,
      "grad_norm": 0.3451385796070099,
      "learning_rate": 0.00012,
      "loss": 2.5942,
      "step": 6
    },
    {
      "epoch": 0.00020233016911429968,
      "eval_loss": 0.68121337890625,
      "eval_runtime": 862.7008,
      "eval_samples_per_second": 14.474,
      "eval_steps_per_second": 7.238,
      "step": 6
    },
    {
      "epoch": 0.00023605186396668295,
      "grad_norm": 0.41344591975212097,
      "learning_rate": 0.00014,
      "loss": 2.7154,
      "step": 7
    },
    {
      "epoch": 0.0002697735588190662,
      "grad_norm": 0.5241850018501282,
      "learning_rate": 0.00016,
      "loss": 2.9489,
      "step": 8
    },
    {
      "epoch": 0.00030349525367144955,
      "grad_norm": 0.5558117032051086,
      "learning_rate": 0.00018,
      "loss": 3.2723,
      "step": 9
    },
    {
      "epoch": 0.00030349525367144955,
      "eval_loss": 0.6600808501243591,
      "eval_runtime": 862.9465,
      "eval_samples_per_second": 14.47,
      "eval_steps_per_second": 7.236,
      "step": 9
    },
    {
      "epoch": 0.0003372169485238328,
      "grad_norm": 0.6537790298461914,
      "learning_rate": 0.0002,
      "loss": 3.3477,
      "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": 3257498484080640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}