{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10040160642570281,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002008032128514056,
      "eval_loss": 1.3564062118530273,
      "eval_runtime": 15.0793,
      "eval_samples_per_second": 13.926,
      "eval_steps_per_second": 6.963,
      "step": 1
    },
    {
      "epoch": 0.010040160642570281,
      "grad_norm": 0.5504012107849121,
      "learning_rate": 5e-05,
      "loss": 1.3271,
      "step": 5
    },
    {
      "epoch": 0.020080321285140562,
      "grad_norm": 0.6484191417694092,
      "learning_rate": 0.0001,
      "loss": 1.1678,
      "step": 10
    },
    {
      "epoch": 0.020080321285140562,
      "eval_loss": 1.2729361057281494,
      "eval_runtime": 15.2427,
      "eval_samples_per_second": 13.777,
      "eval_steps_per_second": 6.889,
      "step": 10
    },
    {
      "epoch": 0.030120481927710843,
      "grad_norm": 1.15849769115448,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2379,
      "step": 15
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 0.7769501805305481,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2023,
      "step": 20
    },
    {
      "epoch": 0.040160642570281124,
      "eval_loss": 1.1557728052139282,
      "eval_runtime": 15.2737,
      "eval_samples_per_second": 13.749,
      "eval_steps_per_second": 6.875,
      "step": 20
    },
    {
      "epoch": 0.050200803212851405,
      "grad_norm": 0.73304682970047,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0819,
      "step": 25
    },
    {
      "epoch": 0.060240963855421686,
      "grad_norm": 1.0948939323425293,
      "learning_rate": 5e-05,
      "loss": 1.0014,
      "step": 30
    },
    {
      "epoch": 0.060240963855421686,
      "eval_loss": 1.0921810865402222,
      "eval_runtime": 15.4103,
      "eval_samples_per_second": 13.627,
      "eval_steps_per_second": 6.814,
      "step": 30
    },
    {
      "epoch": 0.07028112449799197,
      "grad_norm": 0.9539682269096375,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0629,
      "step": 35
    },
    {
      "epoch": 0.08032128514056225,
      "grad_norm": 0.7001964449882507,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.973,
      "step": 40
    },
    {
      "epoch": 0.08032128514056225,
      "eval_loss": 1.071045994758606,
      "eval_runtime": 15.4237,
      "eval_samples_per_second": 13.615,
      "eval_steps_per_second": 6.808,
      "step": 40
    },
    {
      "epoch": 0.09036144578313253,
      "grad_norm": 1.067579984664917,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1202,
      "step": 45
    },
    {
      "epoch": 0.10040160642570281,
      "grad_norm": 0.6732654571533203,
      "learning_rate": 0.0,
      "loss": 0.9958,
      "step": 50
    },
    {
      "epoch": 0.10040160642570281,
      "eval_loss": 1.0679703950881958,
      "eval_runtime": 15.393,
      "eval_samples_per_second": 13.643,
      "eval_steps_per_second": 6.821,
      "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": 1.0681233533042688e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}