{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03568242640499554,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007136485280999108,
      "eval_loss": 4.1770219802856445,
      "eval_runtime": 39.0571,
      "eval_samples_per_second": 15.106,
      "eval_steps_per_second": 7.553,
      "step": 1
    },
    {
      "epoch": 0.003568242640499554,
      "grad_norm": 2.147374153137207,
      "learning_rate": 5e-05,
      "loss": 4.1219,
      "step": 5
    },
    {
      "epoch": 0.007136485280999108,
      "grad_norm": 2.610384225845337,
      "learning_rate": 0.0001,
      "loss": 3.7342,
      "step": 10
    },
    {
      "epoch": 0.007136485280999108,
      "eval_loss": 3.428222179412842,
      "eval_runtime": 39.3068,
      "eval_samples_per_second": 15.01,
      "eval_steps_per_second": 7.505,
      "step": 10
    },
    {
      "epoch": 0.010704727921498661,
      "grad_norm": 2.355562210083008,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7551,
      "step": 15
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": 2.9461042881011963,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8547,
      "step": 20
    },
    {
      "epoch": 0.014272970561998216,
      "eval_loss": 1.55669105052948,
      "eval_runtime": 39.3365,
      "eval_samples_per_second": 14.999,
      "eval_steps_per_second": 7.499,
      "step": 20
    },
    {
      "epoch": 0.01784121320249777,
      "grad_norm": 2.520334005355835,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5225,
      "step": 25
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 2.5305795669555664,
      "learning_rate": 5e-05,
      "loss": 1.3177,
      "step": 30
    },
    {
      "epoch": 0.021409455842997322,
      "eval_loss": 1.2350683212280273,
      "eval_runtime": 39.4794,
      "eval_samples_per_second": 14.944,
      "eval_steps_per_second": 7.472,
      "step": 30
    },
    {
      "epoch": 0.024977698483496878,
      "grad_norm": 2.365730047225952,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.1974,
      "step": 35
    },
    {
      "epoch": 0.028545941123996433,
      "grad_norm": 1.927002191543579,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1119,
      "step": 40
    },
    {
      "epoch": 0.028545941123996433,
      "eval_loss": 1.1479406356811523,
      "eval_runtime": 39.5706,
      "eval_samples_per_second": 14.91,
      "eval_steps_per_second": 7.455,
      "step": 40
    },
    {
      "epoch": 0.032114183764495985,
      "grad_norm": 2.129756450653076,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1849,
      "step": 45
    },
    {
      "epoch": 0.03568242640499554,
      "grad_norm": 2.1976375579833984,
      "learning_rate": 0.0,
      "loss": 1.1207,
      "step": 50
    },
    {
      "epoch": 0.03568242640499554,
      "eval_loss": 1.1337636709213257,
      "eval_runtime": 39.4315,
      "eval_samples_per_second": 14.963,
      "eval_steps_per_second": 7.481,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}