{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13966480446927373,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002793296089385475,
      "eval_loss": 9.896864891052246,
      "eval_runtime": 4.9175,
      "eval_samples_per_second": 30.707,
      "eval_steps_per_second": 15.455,
      "step": 1
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 41.86698532104492,
      "learning_rate": 5e-05,
      "loss": 8.7545,
      "step": 5
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 15.126924514770508,
      "learning_rate": 0.0001,
      "loss": 7.191,
      "step": 10
    },
    {
      "epoch": 0.027932960893854747,
      "eval_loss": 5.595855712890625,
      "eval_runtime": 4.8333,
      "eval_samples_per_second": 31.241,
      "eval_steps_per_second": 15.724,
      "step": 10
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 4.385186672210693,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.0465,
      "step": 15
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 3.310457706451416,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.4644,
      "step": 20
    },
    {
      "epoch": 0.055865921787709494,
      "eval_loss": 4.217800617218018,
      "eval_runtime": 4.9043,
      "eval_samples_per_second": 30.789,
      "eval_steps_per_second": 15.497,
      "step": 20
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 3.4962682723999023,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.1238,
      "step": 25
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 3.5850486755371094,
      "learning_rate": 5e-05,
      "loss": 3.7438,
      "step": 30
    },
    {
      "epoch": 0.08379888268156424,
      "eval_loss": 3.5863335132598877,
      "eval_runtime": 4.88,
      "eval_samples_per_second": 30.942,
      "eval_steps_per_second": 15.574,
      "step": 30
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 3.6995723247528076,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.3512,
      "step": 35
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 3.8023898601531982,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.2392,
      "step": 40
    },
    {
      "epoch": 0.11173184357541899,
      "eval_loss": 3.2825071811676025,
      "eval_runtime": 4.8262,
      "eval_samples_per_second": 31.287,
      "eval_steps_per_second": 15.747,
      "step": 40
    },
    {
      "epoch": 0.12569832402234637,
      "grad_norm": 4.109200477600098,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.2066,
      "step": 45
    },
    {
      "epoch": 0.13966480446927373,
      "grad_norm": 2.853254795074463,
      "learning_rate": 0.0,
      "loss": 3.1558,
      "step": 50
    },
    {
      "epoch": 0.13966480446927373,
      "eval_loss": 3.2231385707855225,
      "eval_runtime": 4.8098,
      "eval_samples_per_second": 31.394,
      "eval_steps_per_second": 15.801,
      "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": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}