{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008838372678822375,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.767674535764475e-05,
      "eval_loss": 0.6415814161300659,
      "eval_runtime": 2778.8038,
      "eval_samples_per_second": 8.572,
      "eval_steps_per_second": 4.286,
      "step": 1
    },
    {
      "epoch": 8.838372678822376e-05,
      "grad_norm": 3.4858734607696533,
      "learning_rate": 5e-05,
      "loss": 2.4752,
      "step": 5
    },
    {
      "epoch": 0.00017676745357644752,
      "grad_norm": 3.3754613399505615,
      "learning_rate": 0.0001,
      "loss": 2.352,
      "step": 10
    },
    {
      "epoch": 0.00017676745357644752,
      "eval_loss": 0.49333542585372925,
      "eval_runtime": 2791.4488,
      "eval_samples_per_second": 8.533,
      "eval_steps_per_second": 4.267,
      "step": 10
    },
    {
      "epoch": 0.00026515118036467126,
      "grad_norm": 1.7720001935958862,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9218,
      "step": 15
    },
    {
      "epoch": 0.00035353490715289503,
      "grad_norm": 1.5975571870803833,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8365,
      "step": 20
    },
    {
      "epoch": 0.00035353490715289503,
      "eval_loss": 0.4407189190387726,
      "eval_runtime": 2788.9982,
      "eval_samples_per_second": 8.541,
      "eval_steps_per_second": 4.27,
      "step": 20
    },
    {
      "epoch": 0.00044191863394111875,
      "grad_norm": 2.09082293510437,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7772,
      "step": 25
    },
    {
      "epoch": 0.0005303023607293425,
      "grad_norm": 1.9168312549591064,
      "learning_rate": 5e-05,
      "loss": 1.8138,
      "step": 30
    },
    {
      "epoch": 0.0005303023607293425,
      "eval_loss": 0.4229850471019745,
      "eval_runtime": 2786.2983,
      "eval_samples_per_second": 8.549,
      "eval_steps_per_second": 4.274,
      "step": 30
    },
    {
      "epoch": 0.0006186860875175662,
      "grad_norm": 2.048436403274536,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6385,
      "step": 35
    },
    {
      "epoch": 0.0007070698143057901,
      "grad_norm": 1.7828311920166016,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.7171,
      "step": 40
    },
    {
      "epoch": 0.0007070698143057901,
      "eval_loss": 0.4164840579032898,
      "eval_runtime": 2784.4097,
      "eval_samples_per_second": 8.555,
      "eval_steps_per_second": 4.277,
      "step": 40
    },
    {
      "epoch": 0.0007954535410940138,
      "grad_norm": 2.1654415130615234,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7822,
      "step": 45
    },
    {
      "epoch": 0.0008838372678822375,
      "grad_norm": 2.121535062789917,
      "learning_rate": 0.0,
      "loss": 1.901,
      "step": 50
    },
    {
      "epoch": 0.0008838372678822375,
      "eval_loss": 0.41538774967193604,
      "eval_runtime": 2784.1147,
      "eval_samples_per_second": 8.556,
      "eval_steps_per_second": 4.278,
      "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": 1.7000916452376576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}