{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015218769816106531,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "grad_norm": 9.900299072265625,
      "learning_rate": 2e-05,
      "loss": 4.6538,
      "step": 1
    },
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 4.714530944824219,
      "eval_runtime": 50.0027,
      "eval_samples_per_second": 49.797,
      "eval_steps_per_second": 24.899,
      "step": 1
    },
    {
      "epoch": 0.0003381948848023674,
      "grad_norm": 9.44548511505127,
      "learning_rate": 4e-05,
      "loss": 4.5746,
      "step": 2
    },
    {
      "epoch": 0.000507292327203551,
      "grad_norm": 10.906355857849121,
      "learning_rate": 6e-05,
      "loss": 4.5136,
      "step": 3
    },
    {
      "epoch": 0.000507292327203551,
      "eval_loss": 4.610001564025879,
      "eval_runtime": 49.1907,
      "eval_samples_per_second": 50.619,
      "eval_steps_per_second": 25.31,
      "step": 3
    },
    {
      "epoch": 0.0006763897696047348,
      "grad_norm": 8.91230297088623,
      "learning_rate": 8e-05,
      "loss": 4.5228,
      "step": 4
    },
    {
      "epoch": 0.0008454872120059184,
      "grad_norm": 11.815821647644043,
      "learning_rate": 0.0001,
      "loss": 4.0529,
      "step": 5
    },
    {
      "epoch": 0.001014584654407102,
      "grad_norm": 9.638334274291992,
      "learning_rate": 0.00012,
      "loss": 3.8741,
      "step": 6
    },
    {
      "epoch": 0.001014584654407102,
      "eval_loss": 3.29811429977417,
      "eval_runtime": 49.4464,
      "eval_samples_per_second": 50.358,
      "eval_steps_per_second": 25.179,
      "step": 6
    },
    {
      "epoch": 0.0011836820968082857,
      "grad_norm": 12.083013534545898,
      "learning_rate": 0.00014,
      "loss": 3.1622,
      "step": 7
    },
    {
      "epoch": 0.0013527795392094695,
      "grad_norm": 15.271347045898438,
      "learning_rate": 0.00016,
      "loss": 2.8997,
      "step": 8
    },
    {
      "epoch": 0.0015218769816106531,
      "grad_norm": 14.881523132324219,
      "learning_rate": 0.00018,
      "loss": 2.082,
      "step": 9
    },
    {
      "epoch": 0.0015218769816106531,
      "eval_loss": 1.534995436668396,
      "eval_runtime": 48.8059,
      "eval_samples_per_second": 51.018,
      "eval_steps_per_second": 25.509,
      "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": 95716026089472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}