{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.96674011921281e-05,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.96674011921281e-06,
      "grad_norm": 0.8414298892021179,
      "learning_rate": 2e-05,
      "loss": 5.5974,
      "step": 1
    },
    {
      "epoch": 8.96674011921281e-06,
      "eval_loss": 5.663151741027832,
      "eval_runtime": 818.4137,
      "eval_samples_per_second": 57.377,
      "eval_steps_per_second": 28.688,
      "step": 1
    },
    {
      "epoch": 1.793348023842562e-05,
      "grad_norm": 0.8906810879707336,
      "learning_rate": 4e-05,
      "loss": 5.6085,
      "step": 2
    },
    {
      "epoch": 2.690022035763843e-05,
      "grad_norm": 1.0453089475631714,
      "learning_rate": 6e-05,
      "loss": 5.6992,
      "step": 3
    },
    {
      "epoch": 2.690022035763843e-05,
      "eval_loss": 5.654193878173828,
      "eval_runtime": 816.999,
      "eval_samples_per_second": 57.476,
      "eval_steps_per_second": 28.738,
      "step": 3
    },
    {
      "epoch": 3.586696047685124e-05,
      "grad_norm": 0.8920280933380127,
      "learning_rate": 8e-05,
      "loss": 5.6118,
      "step": 4
    },
    {
      "epoch": 4.483370059606405e-05,
      "grad_norm": 1.0253804922103882,
      "learning_rate": 0.0001,
      "loss": 5.5263,
      "step": 5
    },
    {
      "epoch": 5.380044071527686e-05,
      "grad_norm": 1.0259923934936523,
      "learning_rate": 0.00012,
      "loss": 5.5502,
      "step": 6
    },
    {
      "epoch": 5.380044071527686e-05,
      "eval_loss": 5.481605529785156,
      "eval_runtime": 820.4641,
      "eval_samples_per_second": 57.233,
      "eval_steps_per_second": 28.617,
      "step": 6
    },
    {
      "epoch": 6.276718083448967e-05,
      "grad_norm": 1.1843591928482056,
      "learning_rate": 0.00014,
      "loss": 5.5073,
      "step": 7
    },
    {
      "epoch": 7.173392095370249e-05,
      "grad_norm": 1.4818826913833618,
      "learning_rate": 0.00016,
      "loss": 5.2135,
      "step": 8
    },
    {
      "epoch": 8.070066107291529e-05,
      "grad_norm": 1.6008281707763672,
      "learning_rate": 0.00018,
      "loss": 5.0409,
      "step": 9
    },
    {
      "epoch": 8.070066107291529e-05,
      "eval_loss": 4.734639644622803,
      "eval_runtime": 819.5811,
      "eval_samples_per_second": 57.295,
      "eval_steps_per_second": 28.648,
      "step": 9
    },
    {
      "epoch": 8.96674011921281e-05,
      "grad_norm": 2.0921313762664795,
      "learning_rate": 0.0002,
      "loss": 4.6896,
      "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": 324523870126080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}