{
  "best_global_step": null,
  "best_metric": 2.5244338512420654,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 19450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 7.744540691375732,
      "learning_rate": 3.600616966580978e-05,
      "loss": 3.7164,
      "step": 1945
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.2547335624694824,
      "eval_runtime": 24.9102,
      "eval_samples_per_second": 139.14,
      "eval_steps_per_second": 17.423,
      "step": 1945
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.693874359130859,
      "learning_rate": 3.200822622107969e-05,
      "loss": 3.1887,
      "step": 3890
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.0059654712677,
      "eval_runtime": 24.8889,
      "eval_samples_per_second": 139.259,
      "eval_steps_per_second": 17.438,
      "step": 3890
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.287598609924316,
      "learning_rate": 2.8010282776349616e-05,
      "loss": 2.9816,
      "step": 5835
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.8556885719299316,
      "eval_runtime": 24.9739,
      "eval_samples_per_second": 138.785,
      "eval_steps_per_second": 17.378,
      "step": 5835
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.844884872436523,
      "learning_rate": 2.401439588688946e-05,
      "loss": 2.8566,
      "step": 7780
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.7777276039123535,
      "eval_runtime": 24.9528,
      "eval_samples_per_second": 138.902,
      "eval_steps_per_second": 17.393,
      "step": 7780
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.421507835388184,
      "learning_rate": 2.001439588688946e-05,
      "loss": 2.7497,
      "step": 9725
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.706150531768799,
      "eval_runtime": 25.4567,
      "eval_samples_per_second": 136.153,
      "eval_steps_per_second": 17.049,
      "step": 9725
    },
    {
      "epoch": 6.0,
      "grad_norm": 7.025661945343018,
      "learning_rate": 1.6014395886889463e-05,
      "loss": 2.6705,
      "step": 11670
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.644594430923462,
      "eval_runtime": 24.4453,
      "eval_samples_per_second": 141.786,
      "eval_steps_per_second": 17.754,
      "step": 11670
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.462997913360596,
      "learning_rate": 1.201439588688946e-05,
      "loss": 2.6134,
      "step": 13615
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.6067004203796387,
      "eval_runtime": 25.7293,
      "eval_samples_per_second": 134.71,
      "eval_steps_per_second": 16.868,
      "step": 13615
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.885842800140381,
      "learning_rate": 8.016452442159383e-06,
      "loss": 2.5566,
      "step": 15560
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.5567843914031982,
      "eval_runtime": 26.1325,
      "eval_samples_per_second": 132.632,
      "eval_steps_per_second": 16.608,
      "step": 15560
    },
    {
      "epoch": 9.0,
      "grad_norm": 6.753671646118164,
      "learning_rate": 4.02056555269923e-06,
      "loss": 2.5294,
      "step": 17505
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.5612432956695557,
      "eval_runtime": 23.421,
      "eval_samples_per_second": 147.987,
      "eval_steps_per_second": 18.53,
      "step": 17505
    },
    {
      "epoch": 10.0,
      "grad_norm": 7.779834270477295,
      "learning_rate": 2.056555269922879e-08,
      "loss": 2.5018,
      "step": 19450
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.5244338512420654,
      "eval_runtime": 26.3445,
      "eval_samples_per_second": 131.564,
      "eval_steps_per_second": 16.474,
      "step": 19450
    },
    {
      "epoch": 10.0,
      "step": 19450,
      "total_flos": 2.04819897090048e+16,
      "train_loss": 2.836465446256427,
      "train_runtime": 5611.6836,
      "train_samples_per_second": 55.481,
      "train_steps_per_second": 3.466
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.5408458709716797,
      "eval_runtime": 26.4975,
      "eval_samples_per_second": 130.805,
      "eval_steps_per_second": 16.379,
      "step": 19450
    }
  ],
  "logging_steps": 500,
  "max_steps": 19450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.04819897090048e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}