{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1728,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0064,
      "eval_loss": 2.962462902069092,
      "eval_runtime": 14.3886,
      "eval_samples_per_second": 73.113,
      "eval_steps_per_second": 2.293,
      "step": 1
    },
    {
      "epoch": 0.0192,
      "grad_norm": 2.497889995574951,
      "learning_rate": 3e-05,
      "loss": 2.9509,
      "step": 3
    },
    {
      "epoch": 0.0384,
      "grad_norm": 1.9927830696105957,
      "learning_rate": 6e-05,
      "loss": 2.9487,
      "step": 6
    },
    {
      "epoch": 0.0576,
      "grad_norm": 1.110428810119629,
      "learning_rate": 9e-05,
      "loss": 2.6523,
      "step": 9
    },
    {
      "epoch": 0.0576,
      "eval_loss": 2.410982847213745,
      "eval_runtime": 4.6211,
      "eval_samples_per_second": 227.65,
      "eval_steps_per_second": 7.141,
      "step": 9
    },
    {
      "epoch": 0.0768,
      "grad_norm": 1.4526073932647705,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.378,
      "step": 12
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.4305192232131958,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.3302,
      "step": 15
    },
    {
      "epoch": 0.1152,
      "grad_norm": 1.1190311908721924,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.2509,
      "step": 18
    },
    {
      "epoch": 0.1152,
      "eval_loss": 2.1677029132843018,
      "eval_runtime": 4.5951,
      "eval_samples_per_second": 228.939,
      "eval_steps_per_second": 7.182,
      "step": 18
    },
    {
      "epoch": 0.1344,
      "grad_norm": 1.0180203914642334,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.1507,
      "step": 21
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.8608107566833496,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.0623,
      "step": 24
    },
    {
      "epoch": 0.1728,
      "grad_norm": 0.8825973272323608,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.1129,
      "step": 27
    },
    {
      "epoch": 0.1728,
      "eval_loss": 2.0721230506896973,
      "eval_runtime": 4.6294,
      "eval_samples_per_second": 227.245,
      "eval_steps_per_second": 7.128,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.362994477694976e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}