{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016644089267798772,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.8493432519776414e-05,
      "grad_norm": 6.692407131195068,
      "learning_rate": 2e-05,
      "loss": 8.5379,
      "step": 1
    },
    {
      "epoch": 1.8493432519776414e-05,
      "eval_loss": 1.8151832818984985,
      "eval_runtime": 1114.2322,
      "eval_samples_per_second": 20.434,
      "eval_steps_per_second": 10.217,
      "step": 1
    },
    {
      "epoch": 3.698686503955283e-05,
      "grad_norm": 5.424865245819092,
      "learning_rate": 4e-05,
      "loss": 6.6532,
      "step": 2
    },
    {
      "epoch": 5.5480297559329245e-05,
      "grad_norm": 4.132454872131348,
      "learning_rate": 6e-05,
      "loss": 6.8357,
      "step": 3
    },
    {
      "epoch": 5.5480297559329245e-05,
      "eval_loss": 1.8091323375701904,
      "eval_runtime": 1108.7542,
      "eval_samples_per_second": 20.535,
      "eval_steps_per_second": 10.267,
      "step": 3
    },
    {
      "epoch": 7.397373007910566e-05,
      "grad_norm": 3.2487056255340576,
      "learning_rate": 8e-05,
      "loss": 6.7712,
      "step": 4
    },
    {
      "epoch": 9.246716259888207e-05,
      "grad_norm": 8.256885528564453,
      "learning_rate": 0.0001,
      "loss": 9.0347,
      "step": 5
    },
    {
      "epoch": 0.00011096059511865849,
      "grad_norm": 5.495502948760986,
      "learning_rate": 0.00012,
      "loss": 7.4819,
      "step": 6
    },
    {
      "epoch": 0.00011096059511865849,
      "eval_loss": 1.7508128881454468,
      "eval_runtime": 1119.8667,
      "eval_samples_per_second": 20.331,
      "eval_steps_per_second": 10.165,
      "step": 6
    },
    {
      "epoch": 0.0001294540276384349,
      "grad_norm": 3.669551134109497,
      "learning_rate": 0.00014,
      "loss": 6.7205,
      "step": 7
    },
    {
      "epoch": 0.0001479474601582113,
      "grad_norm": 3.312818765640259,
      "learning_rate": 0.00016,
      "loss": 6.0611,
      "step": 8
    },
    {
      "epoch": 0.00016644089267798772,
      "grad_norm": 3.7113163471221924,
      "learning_rate": 0.00018,
      "loss": 6.0469,
      "step": 9
    },
    {
      "epoch": 0.00016644089267798772,
      "eval_loss": 1.647411823272705,
      "eval_runtime": 1108.4452,
      "eval_samples_per_second": 20.54,
      "eval_steps_per_second": 10.27,
      "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": 283643750645760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}