{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01412928293889085,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028258565877781704,
      "eval_loss": 1.151291847229004,
      "eval_runtime": 178.3855,
      "eval_samples_per_second": 8.353,
      "eval_steps_per_second": 4.176,
      "step": 1
    },
    {
      "epoch": 0.001412928293889085,
      "grad_norm": 6.91673469543457,
      "learning_rate": 5e-05,
      "loss": 4.7003,
      "step": 5
    },
    {
      "epoch": 0.00282585658777817,
      "grad_norm": 6.784793376922607,
      "learning_rate": 0.0001,
      "loss": 3.4863,
      "step": 10
    },
    {
      "epoch": 0.00282585658777817,
      "eval_loss": 0.638950526714325,
      "eval_runtime": 179.2534,
      "eval_samples_per_second": 8.312,
      "eval_steps_per_second": 4.156,
      "step": 10
    },
    {
      "epoch": 0.0042387848816672555,
      "grad_norm": 4.463286399841309,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0209,
      "step": 15
    },
    {
      "epoch": 0.00565171317555634,
      "grad_norm": 2.5350608825683594,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6406,
      "step": 20
    },
    {
      "epoch": 0.00565171317555634,
      "eval_loss": 0.3515169620513916,
      "eval_runtime": 179.1491,
      "eval_samples_per_second": 8.317,
      "eval_steps_per_second": 4.159,
      "step": 20
    },
    {
      "epoch": 0.007064641469445425,
      "grad_norm": 2.713797092437744,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3488,
      "step": 25
    },
    {
      "epoch": 0.008477569763334511,
      "grad_norm": 2.1892991065979004,
      "learning_rate": 5e-05,
      "loss": 1.2326,
      "step": 30
    },
    {
      "epoch": 0.008477569763334511,
      "eval_loss": 0.31931397318840027,
      "eval_runtime": 178.5123,
      "eval_samples_per_second": 8.347,
      "eval_steps_per_second": 4.173,
      "step": 30
    },
    {
      "epoch": 0.009890498057223597,
      "grad_norm": 3.244086742401123,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2139,
      "step": 35
    },
    {
      "epoch": 0.01130342635111268,
      "grad_norm": 2.5261893272399902,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2825,
      "step": 40
    },
    {
      "epoch": 0.01130342635111268,
      "eval_loss": 0.30965641140937805,
      "eval_runtime": 179.0772,
      "eval_samples_per_second": 8.32,
      "eval_steps_per_second": 4.16,
      "step": 40
    },
    {
      "epoch": 0.012716354645001766,
      "grad_norm": 2.1651501655578613,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.2036,
      "step": 45
    },
    {
      "epoch": 0.01412928293889085,
      "grad_norm": 2.1650586128234863,
      "learning_rate": 0.0,
      "loss": 1.1455,
      "step": 50
    },
    {
      "epoch": 0.01412928293889085,
      "eval_loss": 0.30758610367774963,
      "eval_runtime": 178.4845,
      "eval_samples_per_second": 8.348,
      "eval_steps_per_second": 4.174,
      "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": 1.75267179921408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}