{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16501650165016502,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033003300330033004,
      "eval_loss": 0.7488853931427002,
      "eval_runtime": 19.7022,
      "eval_samples_per_second": 6.497,
      "eval_steps_per_second": 3.248,
      "step": 1
    },
    {
      "epoch": 0.0165016501650165,
      "grad_norm": 3.9368174076080322,
      "learning_rate": 5e-05,
      "loss": 2.8219,
      "step": 5
    },
    {
      "epoch": 0.033003300330033,
      "grad_norm": 4.35306978225708,
      "learning_rate": 0.0001,
      "loss": 2.5563,
      "step": 10
    },
    {
      "epoch": 0.033003300330033,
      "eval_loss": 0.6635968089103699,
      "eval_runtime": 19.9265,
      "eval_samples_per_second": 6.424,
      "eval_steps_per_second": 3.212,
      "step": 10
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 3.046280860900879,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.2334,
      "step": 15
    },
    {
      "epoch": 0.066006600660066,
      "grad_norm": 2.661982536315918,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3494,
      "step": 20
    },
    {
      "epoch": 0.066006600660066,
      "eval_loss": 0.6079679131507874,
      "eval_runtime": 20.0073,
      "eval_samples_per_second": 6.398,
      "eval_steps_per_second": 3.199,
      "step": 20
    },
    {
      "epoch": 0.08250825082508251,
      "grad_norm": 3.2515509128570557,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2636,
      "step": 25
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 2.502488136291504,
      "learning_rate": 5e-05,
      "loss": 2.3351,
      "step": 30
    },
    {
      "epoch": 0.09900990099009901,
      "eval_loss": 0.5951216220855713,
      "eval_runtime": 20.0481,
      "eval_samples_per_second": 6.385,
      "eval_steps_per_second": 3.192,
      "step": 30
    },
    {
      "epoch": 0.11551155115511551,
      "grad_norm": 2.753608465194702,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.3589,
      "step": 35
    },
    {
      "epoch": 0.132013201320132,
      "grad_norm": 2.7407712936401367,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3514,
      "step": 40
    },
    {
      "epoch": 0.132013201320132,
      "eval_loss": 0.5916140079498291,
      "eval_runtime": 20.0668,
      "eval_samples_per_second": 6.379,
      "eval_steps_per_second": 3.189,
      "step": 40
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 2.506066083908081,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.2329,
      "step": 45
    },
    {
      "epoch": 0.16501650165016502,
      "grad_norm": 2.6105473041534424,
      "learning_rate": 0.0,
      "loss": 2.2213,
      "step": 50
    },
    {
      "epoch": 0.16501650165016502,
      "eval_loss": 0.590599775314331,
      "eval_runtime": 20.062,
      "eval_samples_per_second": 6.38,
      "eval_steps_per_second": 3.19,
      "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": 1.75266978594816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}