{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024623803009575923,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027359781121751026,
      "grad_norm": 1.477272629737854,
      "learning_rate": 2e-05,
      "loss": 9.8447,
      "step": 1
    },
    {
      "epoch": 0.0027359781121751026,
      "eval_loss": 2.319706916809082,
      "eval_runtime": 6.1984,
      "eval_samples_per_second": 24.845,
      "eval_steps_per_second": 12.423,
      "step": 1
    },
    {
      "epoch": 0.005471956224350205,
      "grad_norm": 1.324845314025879,
      "learning_rate": 4e-05,
      "loss": 9.3268,
      "step": 2
    },
    {
      "epoch": 0.008207934336525308,
      "grad_norm": 1.304885745048523,
      "learning_rate": 6e-05,
      "loss": 8.346,
      "step": 3
    },
    {
      "epoch": 0.008207934336525308,
      "eval_loss": 2.316396713256836,
      "eval_runtime": 6.1899,
      "eval_samples_per_second": 24.879,
      "eval_steps_per_second": 12.44,
      "step": 3
    },
    {
      "epoch": 0.01094391244870041,
      "grad_norm": 1.6845327615737915,
      "learning_rate": 8e-05,
      "loss": 9.9813,
      "step": 4
    },
    {
      "epoch": 0.013679890560875513,
      "grad_norm": 1.4942121505737305,
      "learning_rate": 0.0001,
      "loss": 8.2704,
      "step": 5
    },
    {
      "epoch": 0.016415868673050615,
      "grad_norm": 1.735281229019165,
      "learning_rate": 0.00012,
      "loss": 8.8551,
      "step": 6
    },
    {
      "epoch": 0.016415868673050615,
      "eval_loss": 2.2669334411621094,
      "eval_runtime": 6.3486,
      "eval_samples_per_second": 24.257,
      "eval_steps_per_second": 12.129,
      "step": 6
    },
    {
      "epoch": 0.019151846785225718,
      "grad_norm": 2.461836576461792,
      "learning_rate": 0.00014,
      "loss": 9.1362,
      "step": 7
    },
    {
      "epoch": 0.02188782489740082,
      "grad_norm": 1.9313154220581055,
      "learning_rate": 0.00016,
      "loss": 8.3081,
      "step": 8
    },
    {
      "epoch": 0.024623803009575923,
      "grad_norm": 2.00248122215271,
      "learning_rate": 0.00018,
      "loss": 7.9256,
      "step": 9
    },
    {
      "epoch": 0.024623803009575923,
      "eval_loss": 2.111816883087158,
      "eval_runtime": 6.3508,
      "eval_samples_per_second": 24.249,
      "eval_steps_per_second": 12.124,
      "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": 1628733135912960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}