{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018550007729169888,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006183335909723295,
      "eval_loss": 2.2790863513946533,
      "eval_runtime": 310.1402,
      "eval_samples_per_second": 2.196,
      "eval_steps_per_second": 1.1,
      "step": 1
    },
    {
      "epoch": 0.0018550007729169888,
      "grad_norm": 3.5891454219818115,
      "learning_rate": 4e-05,
      "loss": 8.3581,
      "step": 3
    },
    {
      "epoch": 0.003091667954861648,
      "eval_loss": 2.2513253688812256,
      "eval_runtime": 310.0019,
      "eval_samples_per_second": 2.197,
      "eval_steps_per_second": 1.1,
      "step": 5
    },
    {
      "epoch": 0.0037100015458339775,
      "grad_norm": 3.3403127193450928,
      "learning_rate": 8e-05,
      "loss": 8.5606,
      "step": 6
    },
    {
      "epoch": 0.005565002318750966,
      "grad_norm": 5.016414165496826,
      "learning_rate": 0.00012,
      "loss": 9.4898,
      "step": 9
    },
    {
      "epoch": 0.006183335909723296,
      "eval_loss": 2.0538792610168457,
      "eval_runtime": 310.1379,
      "eval_samples_per_second": 2.196,
      "eval_steps_per_second": 1.1,
      "step": 10
    },
    {
      "epoch": 0.007420003091667955,
      "grad_norm": 4.1514787673950195,
      "learning_rate": 0.00016,
      "loss": 8.6799,
      "step": 12
    },
    {
      "epoch": 0.009275003864584944,
      "grad_norm": 3.3260223865509033,
      "learning_rate": 0.0002,
      "loss": 7.9948,
      "step": 15
    },
    {
      "epoch": 0.009275003864584944,
      "eval_loss": 1.8450592756271362,
      "eval_runtime": 309.9719,
      "eval_samples_per_second": 2.197,
      "eval_steps_per_second": 1.1,
      "step": 15
    },
    {
      "epoch": 0.011130004637501932,
      "grad_norm": 3.3581345081329346,
      "learning_rate": 0.00018090169943749476,
      "loss": 7.2519,
      "step": 18
    },
    {
      "epoch": 0.012366671819446591,
      "eval_loss": 1.7316858768463135,
      "eval_runtime": 310.1422,
      "eval_samples_per_second": 2.196,
      "eval_steps_per_second": 1.099,
      "step": 20
    },
    {
      "epoch": 0.01298500541041892,
      "grad_norm": 3.1908483505249023,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.4249,
      "step": 21
    },
    {
      "epoch": 0.01484000618333591,
      "grad_norm": 3.0952506065368652,
      "learning_rate": 6.909830056250527e-05,
      "loss": 6.6318,
      "step": 24
    },
    {
      "epoch": 0.015458339774308239,
      "eval_loss": 1.6776248216629028,
      "eval_runtime": 309.8368,
      "eval_samples_per_second": 2.198,
      "eval_steps_per_second": 1.101,
      "step": 25
    },
    {
      "epoch": 0.016695006956252898,
      "grad_norm": 2.567011594772339,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 6.661,
      "step": 27
    },
    {
      "epoch": 0.018550007729169888,
      "grad_norm": 3.4367024898529053,
      "learning_rate": 0.0,
      "loss": 6.1231,
      "step": 30
    },
    {
      "epoch": 0.018550007729169888,
      "eval_loss": 1.6673802137374878,
      "eval_runtime": 309.8189,
      "eval_samples_per_second": 2.198,
      "eval_steps_per_second": 1.101,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.920218563608576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}