{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016586921850079744,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 7.85447359085083,
      "eval_runtime": 42.8761,
      "eval_samples_per_second": 23.09,
      "eval_steps_per_second": 11.545,
      "step": 1
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 6.92096471786499,
      "learning_rate": 5e-05,
      "loss": 8.2487,
      "step": 5
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 7.996544361114502,
      "learning_rate": 0.0001,
      "loss": 7.296,
      "step": 10
    },
    {
      "epoch": 0.004253056884635832,
      "eval_loss": 6.555741786956787,
      "eval_runtime": 42.017,
      "eval_samples_per_second": 23.562,
      "eval_steps_per_second": 11.781,
      "step": 10
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 8.405237197875977,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.7595,
      "step": 15
    },
    {
      "epoch": 0.008506113769271665,
      "grad_norm": 3.423091411590576,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.2915,
      "step": 20
    },
    {
      "epoch": 0.008506113769271665,
      "eval_loss": 3.1996655464172363,
      "eval_runtime": 41.9043,
      "eval_samples_per_second": 23.625,
      "eval_steps_per_second": 11.813,
      "step": 20
    },
    {
      "epoch": 0.01063264221158958,
      "grad_norm": 4.0305705070495605,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.7952,
      "step": 25
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 8.149195671081543,
      "learning_rate": 5e-05,
      "loss": 3.42,
      "step": 30
    },
    {
      "epoch": 0.012759170653907496,
      "eval_loss": 2.458000898361206,
      "eval_runtime": 41.9164,
      "eval_samples_per_second": 23.618,
      "eval_steps_per_second": 11.809,
      "step": 30
    },
    {
      "epoch": 0.014885699096225412,
      "grad_norm": 3.334670066833496,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.7604,
      "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": 1905252268769280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}