{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23460410557184752,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011730205278592375,
      "grad_norm": 0.691848874092102,
      "learning_rate": 1e-05,
      "loss": 2.4378,
      "step": 1
    },
    {
      "epoch": 0.011730205278592375,
      "eval_loss": 2.587639808654785,
      "eval_runtime": 51.588,
      "eval_samples_per_second": 2.791,
      "eval_steps_per_second": 1.396,
      "step": 1
    },
    {
      "epoch": 0.02346041055718475,
      "grad_norm": 0.6807526350021362,
      "learning_rate": 2e-05,
      "loss": 2.4251,
      "step": 2
    },
    {
      "epoch": 0.03519061583577713,
      "grad_norm": 0.6608549356460571,
      "learning_rate": 3e-05,
      "loss": 2.5064,
      "step": 3
    },
    {
      "epoch": 0.0469208211143695,
      "grad_norm": 0.663092315196991,
      "learning_rate": 4e-05,
      "loss": 2.4951,
      "step": 4
    },
    {
      "epoch": 0.05865102639296188,
      "grad_norm": 0.6360378265380859,
      "learning_rate": 5e-05,
      "loss": 2.5327,
      "step": 5
    },
    {
      "epoch": 0.05865102639296188,
      "eval_loss": 2.5367274284362793,
      "eval_runtime": 3.1571,
      "eval_samples_per_second": 45.612,
      "eval_steps_per_second": 22.806,
      "step": 5
    },
    {
      "epoch": 0.07038123167155426,
      "grad_norm": 0.5941628217697144,
      "learning_rate": 6e-05,
      "loss": 2.4586,
      "step": 6
    },
    {
      "epoch": 0.08211143695014662,
      "grad_norm": 0.5375033617019653,
      "learning_rate": 7e-05,
      "loss": 2.4192,
      "step": 7
    },
    {
      "epoch": 0.093841642228739,
      "grad_norm": 0.5819901823997498,
      "learning_rate": 8e-05,
      "loss": 2.448,
      "step": 8
    },
    {
      "epoch": 0.10557184750733138,
      "grad_norm": 0.671298623085022,
      "learning_rate": 9e-05,
      "loss": 2.5178,
      "step": 9
    },
    {
      "epoch": 0.11730205278592376,
      "grad_norm": 0.799557089805603,
      "learning_rate": 0.0001,
      "loss": 2.442,
      "step": 10
    },
    {
      "epoch": 0.11730205278592376,
      "eval_loss": 2.4248690605163574,
      "eval_runtime": 3.1819,
      "eval_samples_per_second": 45.256,
      "eval_steps_per_second": 22.628,
      "step": 10
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.9128552675247192,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3762,
      "step": 11
    },
    {
      "epoch": 0.14076246334310852,
      "grad_norm": 0.6775148510932922,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3551,
      "step": 12
    },
    {
      "epoch": 0.15249266862170088,
      "grad_norm": 0.6293225288391113,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.3521,
      "step": 13
    },
    {
      "epoch": 0.16422287390029325,
      "grad_norm": 0.6110206842422485,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1611,
      "step": 14
    },
    {
      "epoch": 0.17595307917888564,
      "grad_norm": 0.7426127195358276,
      "learning_rate": 5e-05,
      "loss": 2.254,
      "step": 15
    },
    {
      "epoch": 0.17595307917888564,
      "eval_loss": 2.3244590759277344,
      "eval_runtime": 3.1977,
      "eval_samples_per_second": 45.032,
      "eval_steps_per_second": 22.516,
      "step": 15
    },
    {
      "epoch": 0.187683284457478,
      "grad_norm": 0.6948055624961853,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.2583,
      "step": 16
    },
    {
      "epoch": 0.19941348973607037,
      "grad_norm": 0.7502318024635315,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1738,
      "step": 17
    },
    {
      "epoch": 0.21114369501466276,
      "grad_norm": 0.7539845108985901,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.3675,
      "step": 18
    },
    {
      "epoch": 0.22287390029325513,
      "grad_norm": 0.5842881202697754,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.203,
      "step": 19
    },
    {
      "epoch": 0.23460410557184752,
      "grad_norm": 0.7040356397628784,
      "learning_rate": 0.0,
      "loss": 2.2378,
      "step": 20
    },
    {
      "epoch": 0.23460410557184752,
      "eval_loss": 2.292527914047241,
      "eval_runtime": 3.1795,
      "eval_samples_per_second": 45.291,
      "eval_steps_per_second": 22.645,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2618708437499904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}