{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007963051441312311,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.963051441312311e-05,
      "grad_norm": 1.5191630125045776,
      "learning_rate": 2e-05,
      "loss": 3.8787,
      "step": 1
    },
    {
      "epoch": 7.963051441312311e-05,
      "eval_loss": 0.8124251961708069,
      "eval_runtime": 879.7829,
      "eval_samples_per_second": 6.011,
      "eval_steps_per_second": 3.005,
      "step": 1
    },
    {
      "epoch": 0.00015926102882624622,
      "grad_norm": 1.7033369541168213,
      "learning_rate": 4e-05,
      "loss": 3.927,
      "step": 2
    },
    {
      "epoch": 0.00023889154323936931,
      "grad_norm": 1.113368034362793,
      "learning_rate": 6e-05,
      "loss": 2.6541,
      "step": 3
    },
    {
      "epoch": 0.00023889154323936931,
      "eval_loss": 0.8114170432090759,
      "eval_runtime": 876.9563,
      "eval_samples_per_second": 6.03,
      "eval_steps_per_second": 3.015,
      "step": 3
    },
    {
      "epoch": 0.00031852205765249244,
      "grad_norm": 0.9593744277954102,
      "learning_rate": 8e-05,
      "loss": 2.4366,
      "step": 4
    },
    {
      "epoch": 0.00039815257206561556,
      "grad_norm": 1.5424346923828125,
      "learning_rate": 0.0001,
      "loss": 2.9321,
      "step": 5
    },
    {
      "epoch": 0.00047778308647873863,
      "grad_norm": 1.9658819437026978,
      "learning_rate": 0.00012,
      "loss": 3.0287,
      "step": 6
    },
    {
      "epoch": 0.00047778308647873863,
      "eval_loss": 0.7310737371444702,
      "eval_runtime": 875.567,
      "eval_samples_per_second": 6.04,
      "eval_steps_per_second": 3.02,
      "step": 6
    },
    {
      "epoch": 0.0005574136008918618,
      "grad_norm": 2.145761013031006,
      "learning_rate": 0.00014,
      "loss": 2.7298,
      "step": 7
    },
    {
      "epoch": 0.0006370441153049849,
      "grad_norm": 3.19063663482666,
      "learning_rate": 0.00016,
      "loss": 2.9693,
      "step": 8
    },
    {
      "epoch": 0.000716674629718108,
      "grad_norm": 3.2775590419769287,
      "learning_rate": 0.00018,
      "loss": 2.3225,
      "step": 9
    },
    {
      "epoch": 0.000716674629718108,
      "eval_loss": 0.4612276256084442,
      "eval_runtime": 875.7406,
      "eval_samples_per_second": 6.038,
      "eval_steps_per_second": 3.019,
      "step": 9
    },
    {
      "epoch": 0.0007963051441312311,
      "grad_norm": 3.515660285949707,
      "learning_rate": 0.0002,
      "loss": 1.6721,
      "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": 1632478030725120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}