{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004155604294124437,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004617338104582708,
      "grad_norm": 2.8869314193725586,
      "learning_rate": 2e-05,
      "loss": 3.6808,
      "step": 1
    },
    {
      "epoch": 0.0004617338104582708,
      "eval_loss": 4.038337230682373,
      "eval_runtime": 18.3082,
      "eval_samples_per_second": 49.814,
      "eval_steps_per_second": 24.907,
      "step": 1
    },
    {
      "epoch": 0.0009234676209165416,
      "grad_norm": 3.284072160720825,
      "learning_rate": 4e-05,
      "loss": 4.3725,
      "step": 2
    },
    {
      "epoch": 0.0013852014313748124,
      "grad_norm": 2.866499185562134,
      "learning_rate": 6e-05,
      "loss": 4.2589,
      "step": 3
    },
    {
      "epoch": 0.0013852014313748124,
      "eval_loss": 4.023446559906006,
      "eval_runtime": 17.7717,
      "eval_samples_per_second": 51.318,
      "eval_steps_per_second": 25.659,
      "step": 3
    },
    {
      "epoch": 0.0018469352418330831,
      "grad_norm": 3.2831156253814697,
      "learning_rate": 8e-05,
      "loss": 3.8543,
      "step": 4
    },
    {
      "epoch": 0.002308669052291354,
      "grad_norm": 2.9065184593200684,
      "learning_rate": 0.0001,
      "loss": 3.4665,
      "step": 5
    },
    {
      "epoch": 0.0027704028627496247,
      "grad_norm": 3.7608373165130615,
      "learning_rate": 0.00012,
      "loss": 4.4131,
      "step": 6
    },
    {
      "epoch": 0.0027704028627496247,
      "eval_loss": 3.7788474559783936,
      "eval_runtime": 17.9858,
      "eval_samples_per_second": 50.707,
      "eval_steps_per_second": 25.353,
      "step": 6
    },
    {
      "epoch": 0.0032321366732078957,
      "grad_norm": 3.2905681133270264,
      "learning_rate": 0.00014,
      "loss": 4.0498,
      "step": 7
    },
    {
      "epoch": 0.0036938704836661663,
      "grad_norm": 3.312486410140991,
      "learning_rate": 0.00016,
      "loss": 3.2171,
      "step": 8
    },
    {
      "epoch": 0.004155604294124437,
      "grad_norm": 3.6866278648376465,
      "learning_rate": 0.00018,
      "loss": 2.7552,
      "step": 9
    },
    {
      "epoch": 0.004155604294124437,
      "eval_loss": 2.866384506225586,
      "eval_runtime": 18.0474,
      "eval_samples_per_second": 50.534,
      "eval_steps_per_second": 25.267,
      "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": 291868432662528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}