{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02336448598130841,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002336448598130841,
      "grad_norm": 0.5048536658287048,
      "learning_rate": 2e-05,
      "loss": 2.1463,
      "step": 1
    },
    {
      "epoch": 0.002336448598130841,
      "eval_loss": 3.0198140144348145,
      "eval_runtime": 9.9404,
      "eval_samples_per_second": 72.532,
      "eval_steps_per_second": 9.155,
      "step": 1
    },
    {
      "epoch": 0.004672897196261682,
      "grad_norm": 0.5266444683074951,
      "learning_rate": 4e-05,
      "loss": 2.3888,
      "step": 2
    },
    {
      "epoch": 0.007009345794392523,
      "grad_norm": 0.6641351580619812,
      "learning_rate": 6e-05,
      "loss": 2.6798,
      "step": 3
    },
    {
      "epoch": 0.007009345794392523,
      "eval_loss": 2.999393939971924,
      "eval_runtime": 9.1552,
      "eval_samples_per_second": 78.753,
      "eval_steps_per_second": 9.94,
      "step": 3
    },
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 0.5541653633117676,
      "learning_rate": 8e-05,
      "loss": 2.042,
      "step": 4
    },
    {
      "epoch": 0.011682242990654205,
      "grad_norm": 0.6604165434837341,
      "learning_rate": 0.0001,
      "loss": 2.42,
      "step": 5
    },
    {
      "epoch": 0.014018691588785047,
      "grad_norm": 0.5542032122612,
      "learning_rate": 0.00012,
      "loss": 1.8586,
      "step": 6
    },
    {
      "epoch": 0.014018691588785047,
      "eval_loss": 2.883108377456665,
      "eval_runtime": 9.1634,
      "eval_samples_per_second": 78.683,
      "eval_steps_per_second": 9.931,
      "step": 6
    },
    {
      "epoch": 0.016355140186915886,
      "grad_norm": 0.8447181582450867,
      "learning_rate": 0.00014,
      "loss": 2.1857,
      "step": 7
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 1.064998745918274,
      "learning_rate": 0.00016,
      "loss": 2.2227,
      "step": 8
    },
    {
      "epoch": 0.02102803738317757,
      "grad_norm": 1.8660669326782227,
      "learning_rate": 0.00018,
      "loss": 2.5705,
      "step": 9
    },
    {
      "epoch": 0.02102803738317757,
      "eval_loss": 2.6046745777130127,
      "eval_runtime": 9.1641,
      "eval_samples_per_second": 78.677,
      "eval_steps_per_second": 9.93,
      "step": 9
    },
    {
      "epoch": 0.02336448598130841,
      "grad_norm": 0.90097975730896,
      "learning_rate": 0.0002,
      "loss": 1.9405,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.045015069458432e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}