{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5678233438485805,
  "eval_steps": 9,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012618296529968454,
      "eval_loss": 1.88910710811615,
      "eval_runtime": 2.2136,
      "eval_samples_per_second": 60.535,
      "eval_steps_per_second": 7.68,
      "step": 1
    },
    {
      "epoch": 0.03785488958990536,
      "grad_norm": 0.7511712908744812,
      "learning_rate": 3e-05,
      "loss": 1.8139,
      "step": 3
    },
    {
      "epoch": 0.07570977917981073,
      "grad_norm": 0.8463343381881714,
      "learning_rate": 6e-05,
      "loss": 1.9489,
      "step": 6
    },
    {
      "epoch": 0.11356466876971609,
      "grad_norm": 0.9100675582885742,
      "learning_rate": 9e-05,
      "loss": 1.7745,
      "step": 9
    },
    {
      "epoch": 0.11356466876971609,
      "eval_loss": 1.8236573934555054,
      "eval_runtime": 2.232,
      "eval_samples_per_second": 60.036,
      "eval_steps_per_second": 7.617,
      "step": 9
    },
    {
      "epoch": 0.15141955835962145,
      "grad_norm": 0.6830158233642578,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.7182,
      "step": 12
    },
    {
      "epoch": 0.1892744479495268,
      "grad_norm": 0.7045711278915405,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.695,
      "step": 15
    },
    {
      "epoch": 0.22712933753943218,
      "grad_norm": 0.6682664752006531,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.5894,
      "step": 18
    },
    {
      "epoch": 0.22712933753943218,
      "eval_loss": 1.7477922439575195,
      "eval_runtime": 2.2514,
      "eval_samples_per_second": 59.52,
      "eval_steps_per_second": 7.551,
      "step": 18
    },
    {
      "epoch": 0.26498422712933756,
      "grad_norm": 0.6020422577857971,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6764,
      "step": 21
    },
    {
      "epoch": 0.3028391167192429,
      "grad_norm": 0.8476335406303406,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6508,
      "step": 24
    },
    {
      "epoch": 0.34069400630914826,
      "grad_norm": 0.7293965220451355,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.4719,
      "step": 27
    },
    {
      "epoch": 0.34069400630914826,
      "eval_loss": 1.7059693336486816,
      "eval_runtime": 2.2316,
      "eval_samples_per_second": 60.048,
      "eval_steps_per_second": 7.618,
      "step": 27
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 0.6286596059799194,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7276,
      "step": 30
    },
    {
      "epoch": 0.416403785488959,
      "grad_norm": 0.8441144227981567,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8129,
      "step": 33
    },
    {
      "epoch": 0.45425867507886436,
      "grad_norm": 0.6982610821723938,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.8098,
      "step": 36
    },
    {
      "epoch": 0.45425867507886436,
      "eval_loss": 1.6810848712921143,
      "eval_runtime": 2.2408,
      "eval_samples_per_second": 59.8,
      "eval_steps_per_second": 7.587,
      "step": 36
    },
    {
      "epoch": 0.4921135646687697,
      "grad_norm": 0.704291045665741,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.5021,
      "step": 39
    },
    {
      "epoch": 0.5299684542586751,
      "grad_norm": 0.725155234336853,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.712,
      "step": 42
    },
    {
      "epoch": 0.5678233438485805,
      "grad_norm": 0.6382411122322083,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.587,
      "step": 45
    },
    {
      "epoch": 0.5678233438485805,
      "eval_loss": 1.6629996299743652,
      "eval_runtime": 2.2344,
      "eval_samples_per_second": 59.971,
      "eval_steps_per_second": 7.608,
      "step": 45
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3568723789086720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}