{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00034053501835105374,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.7837224261228196e-05,
      "grad_norm": 15.425179481506348,
      "learning_rate": 2e-05,
      "loss": 4.2775,
      "step": 1
    },
    {
      "epoch": 3.7837224261228196e-05,
      "eval_loss": 1.0869630575180054,
      "eval_runtime": 1969.7164,
      "eval_samples_per_second": 2.825,
      "eval_steps_per_second": 2.825,
      "step": 1
    },
    {
      "epoch": 7.567444852245639e-05,
      "grad_norm": 14.54034423828125,
      "learning_rate": 4e-05,
      "loss": 4.198,
      "step": 2
    },
    {
      "epoch": 0.00011351167278368459,
      "grad_norm": 9.865498542785645,
      "learning_rate": 6e-05,
      "loss": 4.3061,
      "step": 3
    },
    {
      "epoch": 0.00011351167278368459,
      "eval_loss": 0.9358382225036621,
      "eval_runtime": 2314.6741,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 3
    },
    {
      "epoch": 0.00015134889704491279,
      "grad_norm": 7.155860424041748,
      "learning_rate": 8e-05,
      "loss": 3.874,
      "step": 4
    },
    {
      "epoch": 0.00018918612130614098,
      "grad_norm": 4.540463924407959,
      "learning_rate": 0.0001,
      "loss": 3.2857,
      "step": 5
    },
    {
      "epoch": 0.00022702334556736918,
      "grad_norm": 3.66566801071167,
      "learning_rate": 0.00012,
      "loss": 3.2424,
      "step": 6
    },
    {
      "epoch": 0.00022702334556736918,
      "eval_loss": 0.7986580729484558,
      "eval_runtime": 2384.8555,
      "eval_samples_per_second": 2.333,
      "eval_steps_per_second": 2.333,
      "step": 6
    },
    {
      "epoch": 0.00026486056982859735,
      "grad_norm": 4.557755470275879,
      "learning_rate": 0.00014,
      "loss": 3.3631,
      "step": 7
    },
    {
      "epoch": 0.00030269779408982557,
      "grad_norm": 3.7365407943725586,
      "learning_rate": 0.00016,
      "loss": 2.95,
      "step": 8
    },
    {
      "epoch": 0.00034053501835105374,
      "grad_norm": 3.51993989944458,
      "learning_rate": 0.00018,
      "loss": 2.4298,
      "step": 9
    },
    {
      "epoch": 0.00034053501835105374,
      "eval_loss": 0.6866493821144104,
      "eval_runtime": 2377.7125,
      "eval_samples_per_second": 2.34,
      "eval_steps_per_second": 2.34,
      "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": 6328165488132096.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}