{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005685856432125089,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005685856432125089,
      "grad_norm": 3.160240411758423,
      "learning_rate": 2e-05,
      "loss": 3.0449,
      "step": 1
    },
    {
      "epoch": 0.0005685856432125089,
      "eval_loss": 2.871772050857544,
      "eval_runtime": 14.3157,
      "eval_samples_per_second": 51.761,
      "eval_steps_per_second": 25.916,
      "step": 1
    },
    {
      "epoch": 0.0011371712864250178,
      "grad_norm": 1.4981428384780884,
      "learning_rate": 4e-05,
      "loss": 2.6713,
      "step": 2
    },
    {
      "epoch": 0.0017057569296375266,
      "grad_norm": 1.4347684383392334,
      "learning_rate": 6e-05,
      "loss": 2.2101,
      "step": 3
    },
    {
      "epoch": 0.0017057569296375266,
      "eval_loss": 2.868518590927124,
      "eval_runtime": 14.2948,
      "eval_samples_per_second": 51.837,
      "eval_steps_per_second": 25.954,
      "step": 3
    },
    {
      "epoch": 0.0022743425728500356,
      "grad_norm": 1.4736236333847046,
      "learning_rate": 8e-05,
      "loss": 2.1447,
      "step": 4
    },
    {
      "epoch": 0.0028429282160625444,
      "grad_norm": 1.3654485940933228,
      "learning_rate": 0.0001,
      "loss": 2.6493,
      "step": 5
    },
    {
      "epoch": 0.003411513859275053,
      "grad_norm": 1.256227731704712,
      "learning_rate": 0.00012,
      "loss": 3.4064,
      "step": 6
    },
    {
      "epoch": 0.003411513859275053,
      "eval_loss": 2.8134679794311523,
      "eval_runtime": 14.3512,
      "eval_samples_per_second": 51.633,
      "eval_steps_per_second": 25.851,
      "step": 6
    },
    {
      "epoch": 0.003980099502487562,
      "grad_norm": 1.8904207944869995,
      "learning_rate": 0.00014,
      "loss": 2.4096,
      "step": 7
    },
    {
      "epoch": 0.004548685145700071,
      "grad_norm": 1.6368253231048584,
      "learning_rate": 0.00016,
      "loss": 2.2356,
      "step": 8
    },
    {
      "epoch": 0.00511727078891258,
      "grad_norm": 1.824141502380371,
      "learning_rate": 0.00018,
      "loss": 1.5396,
      "step": 9
    },
    {
      "epoch": 0.00511727078891258,
      "eval_loss": 2.675954818725586,
      "eval_runtime": 14.3219,
      "eval_samples_per_second": 51.739,
      "eval_steps_per_second": 25.904,
      "step": 9
    },
    {
      "epoch": 0.005685856432125089,
      "grad_norm": 1.601119875907898,
      "learning_rate": 0.0002,
      "loss": 2.8724,
      "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": 526188627886080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}