{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16447368421052633,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003289473684210526,
      "eval_loss": 1.5813665390014648,
      "eval_runtime": 78.8755,
      "eval_samples_per_second": 1.635,
      "eval_steps_per_second": 0.824,
      "step": 1
    },
    {
      "epoch": 0.01644736842105263,
      "grad_norm": 1.7443066835403442,
      "learning_rate": 5e-05,
      "loss": 6.5254,
      "step": 5
    },
    {
      "epoch": 0.03289473684210526,
      "grad_norm": 2.3605740070343018,
      "learning_rate": 0.0001,
      "loss": 6.2149,
      "step": 10
    },
    {
      "epoch": 0.03289473684210526,
      "eval_loss": 1.5433368682861328,
      "eval_runtime": 76.1974,
      "eval_samples_per_second": 1.693,
      "eval_steps_per_second": 0.853,
      "step": 10
    },
    {
      "epoch": 0.049342105263157895,
      "grad_norm": 3.8667151927948,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.0027,
      "step": 15
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 3.2571685314178467,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.018,
      "step": 20
    },
    {
      "epoch": 0.06578947368421052,
      "eval_loss": 1.4255777597427368,
      "eval_runtime": 58.9794,
      "eval_samples_per_second": 2.187,
      "eval_steps_per_second": 1.102,
      "step": 20
    },
    {
      "epoch": 0.08223684210526316,
      "grad_norm": 3.4146549701690674,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.5718,
      "step": 25
    },
    {
      "epoch": 0.09868421052631579,
      "grad_norm": 3.615739345550537,
      "learning_rate": 5e-05,
      "loss": 5.5577,
      "step": 30
    },
    {
      "epoch": 0.09868421052631579,
      "eval_loss": 1.3943980932235718,
      "eval_runtime": 51.6919,
      "eval_samples_per_second": 2.496,
      "eval_steps_per_second": 1.257,
      "step": 30
    },
    {
      "epoch": 0.11513157894736842,
      "grad_norm": 2.7189626693725586,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.6287,
      "step": 35
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 2.727278709411621,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.4495,
      "step": 40
    },
    {
      "epoch": 0.13157894736842105,
      "eval_loss": 1.3894844055175781,
      "eval_runtime": 46.8497,
      "eval_samples_per_second": 2.753,
      "eval_steps_per_second": 1.387,
      "step": 40
    },
    {
      "epoch": 0.14802631578947367,
      "grad_norm": 2.9583241939544678,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.5246,
      "step": 45
    },
    {
      "epoch": 0.16447368421052633,
      "grad_norm": 3.652521848678589,
      "learning_rate": 0.0,
      "loss": 5.0081,
      "step": 50
    },
    {
      "epoch": 0.16447368421052633,
      "eval_loss": 1.388664960861206,
      "eval_runtime": 35.0602,
      "eval_samples_per_second": 3.679,
      "eval_steps_per_second": 1.854,
      "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": 8143665679564800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}