{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1762114537444934,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003524229074889868,
      "eval_loss": 10.389432907104492,
      "eval_runtime": 0.6641,
      "eval_samples_per_second": 180.695,
      "eval_steps_per_second": 90.347,
      "step": 1
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 0.15632955729961395,
      "learning_rate": 5e-05,
      "loss": 10.3702,
      "step": 5
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 0.14511705935001373,
      "learning_rate": 0.0001,
      "loss": 10.3658,
      "step": 10
    },
    {
      "epoch": 0.03524229074889868,
      "eval_loss": 10.388075828552246,
      "eval_runtime": 0.6593,
      "eval_samples_per_second": 181.999,
      "eval_steps_per_second": 90.999,
      "step": 10
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 0.150935098528862,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3722,
      "step": 15
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 0.12443643063306808,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.374,
      "step": 20
    },
    {
      "epoch": 0.07048458149779736,
      "eval_loss": 10.385220527648926,
      "eval_runtime": 0.6536,
      "eval_samples_per_second": 183.601,
      "eval_steps_per_second": 91.801,
      "step": 20
    },
    {
      "epoch": 0.0881057268722467,
      "grad_norm": 0.16687703132629395,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3652,
      "step": 25
    },
    {
      "epoch": 0.10572687224669604,
      "grad_norm": 0.15598571300506592,
      "learning_rate": 5e-05,
      "loss": 10.3712,
      "step": 30
    },
    {
      "epoch": 0.10572687224669604,
      "eval_loss": 10.38306713104248,
      "eval_runtime": 0.6626,
      "eval_samples_per_second": 181.112,
      "eval_steps_per_second": 90.556,
      "step": 30
    },
    {
      "epoch": 0.12334801762114538,
      "grad_norm": 0.13648445904254913,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3727,
      "step": 35
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": 0.16172507405281067,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3741,
      "step": 40
    },
    {
      "epoch": 0.14096916299559473,
      "eval_loss": 10.381892204284668,
      "eval_runtime": 0.6915,
      "eval_samples_per_second": 173.545,
      "eval_steps_per_second": 86.772,
      "step": 40
    },
    {
      "epoch": 0.15859030837004406,
      "grad_norm": 0.15061938762664795,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3903,
      "step": 45
    },
    {
      "epoch": 0.1762114537444934,
      "grad_norm": 0.1517992913722992,
      "learning_rate": 0.0,
      "loss": 10.3721,
      "step": 50
    },
    {
      "epoch": 0.1762114537444934,
      "eval_loss": 10.381696701049805,
      "eval_runtime": 0.6571,
      "eval_samples_per_second": 182.608,
      "eval_steps_per_second": 91.304,
      "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": 646545408000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}