{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9090909090909091,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.4072323441505432,
      "learning_rate": 0.00016,
      "loss": 1.2613,
      "step": 5
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.3422090411186218,
      "learning_rate": 0.00019157894736842104,
      "loss": 0.8695,
      "step": 10
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.2869296967983246,
      "learning_rate": 0.00018105263157894739,
      "loss": 0.5999,
      "step": 15
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.23798972368240356,
      "learning_rate": 0.0001705263157894737,
      "loss": 0.4548,
      "step": 20
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.2759585380554199,
      "learning_rate": 0.00016,
      "loss": 0.3985,
      "step": 25
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.23391029238700867,
      "learning_rate": 0.00014947368421052633,
      "loss": 0.3361,
      "step": 30
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.1920405626296997,
      "learning_rate": 0.00013894736842105264,
      "loss": 0.2902,
      "step": 35
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.21214406192302704,
      "learning_rate": 0.00012842105263157895,
      "loss": 0.2513,
      "step": 40
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.25092971324920654,
      "learning_rate": 0.00011789473684210525,
      "loss": 0.2436,
      "step": 45
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.2771654427051544,
      "learning_rate": 0.00010736842105263158,
      "loss": 0.2444,
      "step": 50
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.21686707437038422,
      "learning_rate": 9.68421052631579e-05,
      "loss": 0.2096,
      "step": 55
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.1858663111925125,
      "learning_rate": 8.631578947368421e-05,
      "loss": 0.2035,
      "step": 60
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.22459319233894348,
      "learning_rate": 7.578947368421054e-05,
      "loss": 0.2301,
      "step": 65
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.2039690762758255,
      "learning_rate": 6.526315789473685e-05,
      "loss": 0.183,
      "step": 70
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.2579270899295807,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 0.2029,
      "step": 75
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.24983692169189453,
      "learning_rate": 4.421052631578947e-05,
      "loss": 0.2034,
      "step": 80
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.18478238582611084,
      "learning_rate": 3.368421052631579e-05,
      "loss": 0.1761,
      "step": 85
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.24213539063930511,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 0.2069,
      "step": 90
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.23089101910591125,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 0.2121,
      "step": 95
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.2502235472202301,
      "learning_rate": 2.105263157894737e-06,
      "loss": 0.1998,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9511686515175424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}