{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.028461647929415114,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005692329585883023,
      "eval_loss": 2.594783067703247,
      "eval_runtime": 50.0206,
      "eval_samples_per_second": 14.794,
      "eval_steps_per_second": 7.397,
      "step": 1
    },
    {
      "epoch": 0.0028461647929415115,
      "grad_norm": 0.8254081606864929,
      "learning_rate": 5e-05,
      "loss": 2.5478,
      "step": 5
    },
    {
      "epoch": 0.005692329585883023,
      "grad_norm": 1.1262776851654053,
      "learning_rate": 0.0001,
      "loss": 2.5109,
      "step": 10
    },
    {
      "epoch": 0.005692329585883023,
      "eval_loss": 2.463014602661133,
      "eval_runtime": 50.2084,
      "eval_samples_per_second": 14.739,
      "eval_steps_per_second": 7.369,
      "step": 10
    },
    {
      "epoch": 0.008538494378824533,
      "grad_norm": 0.9406675100326538,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3919,
      "step": 15
    },
    {
      "epoch": 0.011384659171766046,
      "grad_norm": 0.774755597114563,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3201,
      "step": 20
    },
    {
      "epoch": 0.011384659171766046,
      "eval_loss": 2.358638048171997,
      "eval_runtime": 50.3995,
      "eval_samples_per_second": 14.683,
      "eval_steps_per_second": 7.341,
      "step": 20
    },
    {
      "epoch": 0.014230823964707557,
      "grad_norm": 0.9281075596809387,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.409,
      "step": 25
    },
    {
      "epoch": 0.017076988757649066,
      "grad_norm": 0.739485502243042,
      "learning_rate": 5e-05,
      "loss": 2.2632,
      "step": 30
    },
    {
      "epoch": 0.017076988757649066,
      "eval_loss": 2.3197875022888184,
      "eval_runtime": 50.6305,
      "eval_samples_per_second": 14.616,
      "eval_steps_per_second": 7.308,
      "step": 30
    },
    {
      "epoch": 0.01992315355059058,
      "grad_norm": 0.7782480120658875,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.2961,
      "step": 35
    },
    {
      "epoch": 0.022769318343532092,
      "grad_norm": 0.7364357113838196,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.2941,
      "step": 40
    },
    {
      "epoch": 0.022769318343532092,
      "eval_loss": 2.3098244667053223,
      "eval_runtime": 50.8604,
      "eval_samples_per_second": 14.55,
      "eval_steps_per_second": 7.275,
      "step": 40
    },
    {
      "epoch": 0.0256154831364736,
      "grad_norm": 0.7603503465652466,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.3194,
      "step": 45
    },
    {
      "epoch": 0.028461647929415114,
      "grad_norm": 0.7744248509407043,
      "learning_rate": 0.0,
      "loss": 2.342,
      "step": 50
    },
    {
      "epoch": 0.028461647929415114,
      "eval_loss": 2.307539224624634,
      "eval_runtime": 50.4736,
      "eval_samples_per_second": 14.661,
      "eval_steps_per_second": 7.331,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}