{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4253056884635832,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008506113769271665,
      "eval_loss": 2.6882784366607666,
      "eval_runtime": 13.726,
      "eval_samples_per_second": 57.701,
      "eval_steps_per_second": 7.213,
      "step": 1
    },
    {
      "epoch": 0.08506113769271664,
      "grad_norm": 2.610746383666992,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2492,
      "step": 10
    },
    {
      "epoch": 0.08506113769271664,
      "eval_loss": 1.2946914434432983,
      "eval_runtime": 13.264,
      "eval_samples_per_second": 59.711,
      "eval_steps_per_second": 7.464,
      "step": 10
    },
    {
      "epoch": 0.17012227538543329,
      "grad_norm": 1.2938010692596436,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7155,
      "step": 20
    },
    {
      "epoch": 0.17012227538543329,
      "eval_loss": 0.3049745261669159,
      "eval_runtime": 13.3709,
      "eval_samples_per_second": 59.233,
      "eval_steps_per_second": 7.404,
      "step": 20
    },
    {
      "epoch": 0.2551834130781499,
      "grad_norm": 0.6168785691261292,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.2393,
      "step": 30
    },
    {
      "epoch": 0.2551834130781499,
      "eval_loss": 0.18714644014835358,
      "eval_runtime": 13.3211,
      "eval_samples_per_second": 59.455,
      "eval_steps_per_second": 7.432,
      "step": 30
    },
    {
      "epoch": 0.34024455077086657,
      "grad_norm": 0.5272931456565857,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.2039,
      "step": 40
    },
    {
      "epoch": 0.34024455077086657,
      "eval_loss": 0.1671234667301178,
      "eval_runtime": 13.3113,
      "eval_samples_per_second": 59.499,
      "eval_steps_per_second": 7.437,
      "step": 40
    },
    {
      "epoch": 0.4253056884635832,
      "grad_norm": 0.4160679280757904,
      "learning_rate": 0.0,
      "loss": 0.1855,
      "step": 50
    },
    {
      "epoch": 0.4253056884635832,
      "eval_loss": 0.16490614414215088,
      "eval_runtime": 13.3202,
      "eval_samples_per_second": 59.459,
      "eval_steps_per_second": 7.432,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": 2.5310980472832e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}