{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008115532723856826,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6231065447713652e-05,
      "eval_loss": 1.1903656721115112,
      "eval_runtime": 1380.1159,
      "eval_samples_per_second": 18.797,
      "eval_steps_per_second": 9.398,
      "step": 1
    },
    {
      "epoch": 8.115532723856825e-05,
      "grad_norm": 0.3520669639110565,
      "learning_rate": 5e-05,
      "loss": 0.9505,
      "step": 5
    },
    {
      "epoch": 0.0001623106544771365,
      "grad_norm": 0.2661932110786438,
      "learning_rate": 0.0001,
      "loss": 1.2073,
      "step": 10
    },
    {
      "epoch": 0.0001623106544771365,
      "eval_loss": 1.1880683898925781,
      "eval_runtime": 1378.339,
      "eval_samples_per_second": 18.821,
      "eval_steps_per_second": 9.411,
      "step": 10
    },
    {
      "epoch": 0.00024346598171570477,
      "grad_norm": 0.2401016354560852,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0093,
      "step": 15
    },
    {
      "epoch": 0.000324621308954273,
      "grad_norm": 0.31756964325904846,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.226,
      "step": 20
    },
    {
      "epoch": 0.000324621308954273,
      "eval_loss": 1.172145128250122,
      "eval_runtime": 1379.8373,
      "eval_samples_per_second": 18.801,
      "eval_steps_per_second": 9.4,
      "step": 20
    },
    {
      "epoch": 0.0004057766361928413,
      "grad_norm": 0.275453120470047,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3019,
      "step": 25
    },
    {
      "epoch": 0.00048693196343140954,
      "grad_norm": 0.31876248121261597,
      "learning_rate": 5e-05,
      "loss": 0.9136,
      "step": 30
    },
    {
      "epoch": 0.00048693196343140954,
      "eval_loss": 1.1538145542144775,
      "eval_runtime": 1380.8853,
      "eval_samples_per_second": 18.786,
      "eval_steps_per_second": 9.393,
      "step": 30
    },
    {
      "epoch": 0.0005680872906699778,
      "grad_norm": 0.29820069670677185,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0017,
      "step": 35
    },
    {
      "epoch": 0.000649242617908546,
      "grad_norm": 0.42904895544052124,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1429,
      "step": 40
    },
    {
      "epoch": 0.000649242617908546,
      "eval_loss": 1.1452189683914185,
      "eval_runtime": 1380.8707,
      "eval_samples_per_second": 18.787,
      "eval_steps_per_second": 9.393,
      "step": 40
    },
    {
      "epoch": 0.0007303979451471144,
      "grad_norm": 0.25957685708999634,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1583,
      "step": 45
    },
    {
      "epoch": 0.0008115532723856826,
      "grad_norm": 0.2517766058444977,
      "learning_rate": 0.0,
      "loss": 0.9416,
      "step": 50
    },
    {
      "epoch": 0.0008115532723856826,
      "eval_loss": 1.1437370777130127,
      "eval_runtime": 1383.7319,
      "eval_samples_per_second": 18.748,
      "eval_steps_per_second": 9.374,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6396379586887680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}