{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01606425702811245,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004119040263618577,
      "eval_loss": 0.2545485198497772,
      "eval_runtime": 155.3358,
      "eval_samples_per_second": 6.586,
      "eval_steps_per_second": 3.296,
      "step": 1
    },
    {
      "epoch": 0.0020595201318092883,
      "grad_norm": 4.749020576477051,
      "learning_rate": 5e-05,
      "loss": 1.0407,
      "step": 5
    },
    {
      "epoch": 0.004119040263618577,
      "grad_norm": 2.966028928756714,
      "learning_rate": 0.0001,
      "loss": 0.5506,
      "step": 10
    },
    {
      "epoch": 0.004119040263618577,
      "eval_loss": 0.0800853744149208,
      "eval_runtime": 163.6441,
      "eval_samples_per_second": 6.251,
      "eval_steps_per_second": 3.129,
      "step": 10
    },
    {
      "epoch": 0.006178560395427865,
      "grad_norm": 1.4204341173171997,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2185,
      "step": 15
    },
    {
      "epoch": 0.008238080527237153,
      "grad_norm": 1.414536476135254,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2792,
      "step": 20
    },
    {
      "epoch": 0.008238080527237153,
      "eval_loss": 0.06111093610525131,
      "eval_runtime": 164.1088,
      "eval_samples_per_second": 6.234,
      "eval_steps_per_second": 3.12,
      "step": 20
    },
    {
      "epoch": 0.010297600659046443,
      "grad_norm": 1.4574953317642212,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.2166,
      "step": 25
    },
    {
      "epoch": 0.01235712079085573,
      "grad_norm": 1.1249637603759766,
      "learning_rate": 5e-05,
      "loss": 0.2605,
      "step": 30
    },
    {
      "epoch": 0.01235712079085573,
      "eval_loss": 0.0556037500500679,
      "eval_runtime": 164.1499,
      "eval_samples_per_second": 6.232,
      "eval_steps_per_second": 3.119,
      "step": 30
    },
    {
      "epoch": 0.014416640922665019,
      "grad_norm": 1.0365431308746338,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.182,
      "step": 35
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2186428016427008e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}