{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017504704389304626,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017504704389304627,
      "grad_norm": 0.8464131951332092,
      "learning_rate": 2e-05,
      "loss": 8.7103,
      "step": 1
    },
    {
      "epoch": 0.00017504704389304627,
      "eval_loss": 2.6713948249816895,
      "eval_runtime": 24.2973,
      "eval_samples_per_second": 99.023,
      "eval_steps_per_second": 49.512,
      "step": 1
    },
    {
      "epoch": 0.00035009408778609254,
      "grad_norm": 0.6932229995727539,
      "learning_rate": 4e-05,
      "loss": 9.0147,
      "step": 2
    },
    {
      "epoch": 0.0005251411316791387,
      "grad_norm": 1.0741482973098755,
      "learning_rate": 6e-05,
      "loss": 12.6405,
      "step": 3
    },
    {
      "epoch": 0.0005251411316791387,
      "eval_loss": 2.6700613498687744,
      "eval_runtime": 24.337,
      "eval_samples_per_second": 98.862,
      "eval_steps_per_second": 49.431,
      "step": 3
    },
    {
      "epoch": 0.0007001881755721851,
      "grad_norm": 0.9860628843307495,
      "learning_rate": 8e-05,
      "loss": 12.1232,
      "step": 4
    },
    {
      "epoch": 0.0008752352194652313,
      "grad_norm": 0.8331584334373474,
      "learning_rate": 0.0001,
      "loss": 10.9495,
      "step": 5
    },
    {
      "epoch": 0.0010502822633582775,
      "grad_norm": 1.003852367401123,
      "learning_rate": 0.00012,
      "loss": 11.302,
      "step": 6
    },
    {
      "epoch": 0.0010502822633582775,
      "eval_loss": 2.6650896072387695,
      "eval_runtime": 24.5008,
      "eval_samples_per_second": 98.201,
      "eval_steps_per_second": 49.1,
      "step": 6
    },
    {
      "epoch": 0.0012253293072513238,
      "grad_norm": 1.0521700382232666,
      "learning_rate": 0.00014,
      "loss": 11.3734,
      "step": 7
    },
    {
      "epoch": 0.0014003763511443701,
      "grad_norm": 0.9109848737716675,
      "learning_rate": 0.00016,
      "loss": 11.6143,
      "step": 8
    },
    {
      "epoch": 0.0015754233950374162,
      "grad_norm": 0.8957856297492981,
      "learning_rate": 0.00018,
      "loss": 9.5975,
      "step": 9
    },
    {
      "epoch": 0.0015754233950374162,
      "eval_loss": 2.6437604427337646,
      "eval_runtime": 24.4348,
      "eval_samples_per_second": 98.466,
      "eval_steps_per_second": 49.233,
      "step": 9
    },
    {
      "epoch": 0.0017504704389304626,
      "grad_norm": 0.8883404731750488,
      "learning_rate": 0.0002,
      "loss": 11.0341,
      "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": 28650667769856.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}