{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005187798298402158,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020751193193608634,
      "grad_norm": 1.4039883613586426,
      "learning_rate": 1e-05,
      "loss": 2.1244,
      "step": 1
    },
    {
      "epoch": 0.00020751193193608634,
      "eval_loss": 2.2763936519622803,
      "eval_runtime": 237.6501,
      "eval_samples_per_second": 17.076,
      "eval_steps_per_second": 2.138,
      "step": 1
    },
    {
      "epoch": 0.0004150238638721727,
      "grad_norm": 1.3511576652526855,
      "learning_rate": 2e-05,
      "loss": 2.3025,
      "step": 2
    },
    {
      "epoch": 0.0006225357958082589,
      "grad_norm": 1.3691860437393188,
      "learning_rate": 3e-05,
      "loss": 2.0968,
      "step": 3
    },
    {
      "epoch": 0.0008300477277443454,
      "grad_norm": 1.2978947162628174,
      "learning_rate": 4e-05,
      "loss": 1.891,
      "step": 4
    },
    {
      "epoch": 0.0010375596596804316,
      "grad_norm": 1.3064836263656616,
      "learning_rate": 5e-05,
      "loss": 2.0951,
      "step": 5
    },
    {
      "epoch": 0.0012450715916165179,
      "grad_norm": 1.510711431503296,
      "learning_rate": 6e-05,
      "loss": 2.1635,
      "step": 6
    },
    {
      "epoch": 0.0014525835235526042,
      "grad_norm": 1.724186897277832,
      "learning_rate": 7e-05,
      "loss": 2.3924,
      "step": 7
    },
    {
      "epoch": 0.0016600954554886907,
      "grad_norm": 1.3614786863327026,
      "learning_rate": 8e-05,
      "loss": 2.1578,
      "step": 8
    },
    {
      "epoch": 0.001867607387424777,
      "grad_norm": 1.291449785232544,
      "learning_rate": 9e-05,
      "loss": 2.0637,
      "step": 9
    },
    {
      "epoch": 0.001867607387424777,
      "eval_loss": 1.9984328746795654,
      "eval_runtime": 236.7978,
      "eval_samples_per_second": 17.137,
      "eval_steps_per_second": 2.145,
      "step": 9
    },
    {
      "epoch": 0.002075119319360863,
      "grad_norm": 1.0605844259262085,
      "learning_rate": 0.0001,
      "loss": 1.895,
      "step": 10
    },
    {
      "epoch": 0.0022826312512969496,
      "grad_norm": 1.6267553567886353,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.0418,
      "step": 11
    },
    {
      "epoch": 0.0024901431832330357,
      "grad_norm": 1.5893021821975708,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.9267,
      "step": 12
    },
    {
      "epoch": 0.0026976551151691223,
      "grad_norm": 1.1723555326461792,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8826,
      "step": 13
    },
    {
      "epoch": 0.0029051670471052084,
      "grad_norm": 1.140472173690796,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.9261,
      "step": 14
    },
    {
      "epoch": 0.003112678979041295,
      "grad_norm": 1.1380834579467773,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8419,
      "step": 15
    },
    {
      "epoch": 0.0033201909109773814,
      "grad_norm": 1.0181565284729004,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7555,
      "step": 16
    },
    {
      "epoch": 0.0035277028429134675,
      "grad_norm": 0.8560456037521362,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7858,
      "step": 17
    },
    {
      "epoch": 0.003735214774849554,
      "grad_norm": 1.1353284120559692,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7424,
      "step": 18
    },
    {
      "epoch": 0.003735214774849554,
      "eval_loss": 1.7517411708831787,
      "eval_runtime": 236.5855,
      "eval_samples_per_second": 17.152,
      "eval_steps_per_second": 2.147,
      "step": 18
    },
    {
      "epoch": 0.00394272670678564,
      "grad_norm": 1.1942611932754517,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6209,
      "step": 19
    },
    {
      "epoch": 0.004150238638721726,
      "grad_norm": 1.261995792388916,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.6995,
      "step": 20
    },
    {
      "epoch": 0.004357750570657813,
      "grad_norm": 1.0118539333343506,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.698,
      "step": 21
    },
    {
      "epoch": 0.004565262502593899,
      "grad_norm": 0.9871833920478821,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7638,
      "step": 22
    },
    {
      "epoch": 0.004772774434529985,
      "grad_norm": 1.1649303436279297,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.707,
      "step": 23
    },
    {
      "epoch": 0.0049802863664660715,
      "grad_norm": 1.3631136417388916,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9811,
      "step": 24
    },
    {
      "epoch": 0.005187798298402158,
      "grad_norm": 1.030550479888916,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7537,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0772843939692544e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}