{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.030901287553648068,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034334763948497852,
      "grad_norm": 0.5258381366729736,
      "learning_rate": 2e-05,
      "loss": 0.9653,
      "step": 1
    },
    {
      "epoch": 0.0034334763948497852,
      "eval_loss": 0.9669169187545776,
      "eval_runtime": 8.4335,
      "eval_samples_per_second": 14.585,
      "eval_steps_per_second": 7.352,
      "step": 1
    },
    {
      "epoch": 0.0068669527896995704,
      "grad_norm": 0.5802581906318665,
      "learning_rate": 4e-05,
      "loss": 1.1468,
      "step": 2
    },
    {
      "epoch": 0.010300429184549357,
      "grad_norm": 0.6007038950920105,
      "learning_rate": 6e-05,
      "loss": 0.9214,
      "step": 3
    },
    {
      "epoch": 0.010300429184549357,
      "eval_loss": 0.9642285704612732,
      "eval_runtime": 7.2051,
      "eval_samples_per_second": 17.071,
      "eval_steps_per_second": 8.605,
      "step": 3
    },
    {
      "epoch": 0.013733905579399141,
      "grad_norm": 0.6115662455558777,
      "learning_rate": 8e-05,
      "loss": 0.8596,
      "step": 4
    },
    {
      "epoch": 0.017167381974248927,
      "grad_norm": 0.5410571098327637,
      "learning_rate": 0.0001,
      "loss": 1.0051,
      "step": 5
    },
    {
      "epoch": 0.020600858369098713,
      "grad_norm": 0.6651061177253723,
      "learning_rate": 0.00012,
      "loss": 1.0278,
      "step": 6
    },
    {
      "epoch": 0.020600858369098713,
      "eval_loss": 0.9201897978782654,
      "eval_runtime": 7.2062,
      "eval_samples_per_second": 17.069,
      "eval_steps_per_second": 8.604,
      "step": 6
    },
    {
      "epoch": 0.0240343347639485,
      "grad_norm": 0.5286383628845215,
      "learning_rate": 0.00014,
      "loss": 0.8375,
      "step": 7
    },
    {
      "epoch": 0.027467811158798282,
      "grad_norm": 0.6298297643661499,
      "learning_rate": 0.00016,
      "loss": 1.0884,
      "step": 8
    },
    {
      "epoch": 0.030901287553648068,
      "grad_norm": 0.5216607451438904,
      "learning_rate": 0.00018,
      "loss": 0.7053,
      "step": 9
    },
    {
      "epoch": 0.030901287553648068,
      "eval_loss": 0.8822326064109802,
      "eval_runtime": 7.2091,
      "eval_samples_per_second": 17.062,
      "eval_steps_per_second": 8.6,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3329215646662656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}