{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006385614487682149,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2771228975364299e-05,
      "eval_loss": 2.566653251647949,
      "eval_runtime": 1235.1891,
      "eval_samples_per_second": 26.691,
      "eval_steps_per_second": 13.346,
      "step": 1
    },
    {
      "epoch": 6.38561448768215e-05,
      "grad_norm": 0.48807352781295776,
      "learning_rate": 5e-05,
      "loss": 2.5533,
      "step": 5
    },
    {
      "epoch": 0.000127712289753643,
      "grad_norm": 0.5297641158103943,
      "learning_rate": 0.0001,
      "loss": 2.5952,
      "step": 10
    },
    {
      "epoch": 0.000127712289753643,
      "eval_loss": 2.4731204509735107,
      "eval_runtime": 1235.5847,
      "eval_samples_per_second": 26.683,
      "eval_steps_per_second": 13.342,
      "step": 10
    },
    {
      "epoch": 0.0001915684346304645,
      "grad_norm": 0.6554055213928223,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3075,
      "step": 15
    },
    {
      "epoch": 0.000255424579507286,
      "grad_norm": 1.4760862588882446,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1224,
      "step": 20
    },
    {
      "epoch": 0.000255424579507286,
      "eval_loss": 2.0983011722564697,
      "eval_runtime": 1208.4435,
      "eval_samples_per_second": 27.282,
      "eval_steps_per_second": 13.642,
      "step": 20
    },
    {
      "epoch": 0.00031928072438410746,
      "grad_norm": 0.8199297189712524,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0542,
      "step": 25
    },
    {
      "epoch": 0.000383136869260929,
      "grad_norm": 0.8175716996192932,
      "learning_rate": 5e-05,
      "loss": 2.0226,
      "step": 30
    },
    {
      "epoch": 0.000383136869260929,
      "eval_loss": 1.9621654748916626,
      "eval_runtime": 1211.5072,
      "eval_samples_per_second": 27.213,
      "eval_steps_per_second": 13.607,
      "step": 30
    },
    {
      "epoch": 0.00044699301413775045,
      "grad_norm": 0.8850980401039124,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9742,
      "step": 35
    },
    {
      "epoch": 0.000510849159014572,
      "grad_norm": 0.7436493635177612,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9278,
      "step": 40
    },
    {
      "epoch": 0.000510849159014572,
      "eval_loss": 1.9221231937408447,
      "eval_runtime": 1209.3488,
      "eval_samples_per_second": 27.262,
      "eval_steps_per_second": 13.631,
      "step": 40
    },
    {
      "epoch": 0.0005747053038913935,
      "grad_norm": 0.8459659218788147,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.9795,
      "step": 45
    },
    {
      "epoch": 0.0006385614487682149,
      "grad_norm": 0.8609293699264526,
      "learning_rate": 0.0,
      "loss": 2.0347,
      "step": 50
    },
    {
      "epoch": 0.0006385614487682149,
      "eval_loss": 1.9152170419692993,
      "eval_runtime": 1207.7242,
      "eval_samples_per_second": 27.298,
      "eval_steps_per_second": 13.65,
      "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": 4100243324928000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}