{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.042643923240938165,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014214641080312722,
      "eval_loss": 8.75576400756836,
      "eval_runtime": 17.7008,
      "eval_samples_per_second": 16.779,
      "eval_steps_per_second": 8.418,
      "step": 1
    },
    {
      "epoch": 0.0042643923240938165,
      "grad_norm": 5.729224681854248,
      "learning_rate": 6e-05,
      "loss": 8.8414,
      "step": 3
    },
    {
      "epoch": 0.008528784648187633,
      "grad_norm": 8.158334732055664,
      "learning_rate": 0.00012,
      "loss": 7.4416,
      "step": 6
    },
    {
      "epoch": 0.011371712864250177,
      "eval_loss": 4.816451549530029,
      "eval_runtime": 17.6803,
      "eval_samples_per_second": 16.798,
      "eval_steps_per_second": 8.427,
      "step": 8
    },
    {
      "epoch": 0.01279317697228145,
      "grad_norm": 11.822203636169434,
      "learning_rate": 0.00018,
      "loss": 6.0656,
      "step": 9
    },
    {
      "epoch": 0.017057569296375266,
      "grad_norm": 6.1802825927734375,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.3681,
      "step": 12
    },
    {
      "epoch": 0.021321961620469083,
      "grad_norm": 6.0961737632751465,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6886,
      "step": 15
    },
    {
      "epoch": 0.022743425728500355,
      "eval_loss": 0.3427816331386566,
      "eval_runtime": 17.7463,
      "eval_samples_per_second": 16.736,
      "eval_steps_per_second": 8.396,
      "step": 16
    },
    {
      "epoch": 0.0255863539445629,
      "grad_norm": 6.04608154296875,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.3899,
      "step": 18
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 4.524599552154541,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.1711,
      "step": 21
    },
    {
      "epoch": 0.03411513859275053,
      "grad_norm": 4.087218761444092,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.2142,
      "step": 24
    },
    {
      "epoch": 0.03411513859275053,
      "eval_loss": 0.13798566162586212,
      "eval_runtime": 17.7008,
      "eval_samples_per_second": 16.779,
      "eval_steps_per_second": 8.418,
      "step": 24
    },
    {
      "epoch": 0.03837953091684435,
      "grad_norm": 6.341152191162109,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.1454,
      "step": 27
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 3.5227153301239014,
      "learning_rate": 0.0,
      "loss": 0.1273,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4939038012211200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}