{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0044444444444444444,
      "grad_norm": 16.902174244065552,
      "learning_rate": 8.695652173913044e-07,
      "loss": 2.0963,
      "step": 1
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 7.009398687249402,
      "learning_rate": 4.347826086956522e-06,
      "loss": 2.0386,
      "step": 5
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 3.847165431793462,
      "learning_rate": 8.695652173913044e-06,
      "loss": 1.8407,
      "step": 10
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 1.8435387905194667,
      "learning_rate": 1.3043478260869566e-05,
      "loss": 1.7046,
      "step": 15
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.5416577043323643,
      "learning_rate": 1.739130434782609e-05,
      "loss": 1.6393,
      "step": 20
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.4298947508822206,
      "learning_rate": 1.999516282291988e-05,
      "loss": 1.6362,
      "step": 25
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.3933473839401893,
      "learning_rate": 1.9940798309400527e-05,
      "loss": 1.6027,
      "step": 30
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 1.518431185821292,
      "learning_rate": 1.982635248222264e-05,
      "loss": 1.6116,
      "step": 35
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.4964220141465232,
      "learning_rate": 1.9652517041934357e-05,
      "loss": 1.6207,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.3273747890888088,
      "learning_rate": 1.9420342634699893e-05,
      "loss": 1.5851,
      "step": 45
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.3559947683219293,
      "learning_rate": 1.913123250228619e-05,
      "loss": 1.5698,
      "step": 50
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 1.4346793931071362,
      "learning_rate": 1.878693400099269e-05,
      "loss": 1.5886,
      "step": 55
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.4956510210420204,
      "learning_rate": 1.8389528040783014e-05,
      "loss": 1.5665,
      "step": 60
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 1.2995167467095625,
      "learning_rate": 1.7941416508447537e-05,
      "loss": 1.5525,
      "step": 65
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 1.3135664549473283,
      "learning_rate": 1.7445307750810153e-05,
      "loss": 1.5339,
      "step": 70
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.2301844065790093,
      "learning_rate": 1.690420020571747e-05,
      "loss": 1.5359,
      "step": 75
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.241596243663996,
      "learning_rate": 1.6321364279743267e-05,
      "loss": 1.5251,
      "step": 80
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 1.3171185796153217,
      "learning_rate": 1.570032258213783e-05,
      "loss": 1.5166,
      "step": 85
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2799777894642266,
      "learning_rate": 1.50448286344864e-05,
      "loss": 1.5316,
      "step": 90
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 1.2503649653962412,
      "learning_rate": 1.4358844184753713e-05,
      "loss": 1.5384,
      "step": 95
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.2234087623622982,
      "learning_rate": 1.3646515262826551e-05,
      "loss": 1.5068,
      "step": 100
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 1.2352190020575813,
      "learning_rate": 1.2912147122272523e-05,
      "loss": 1.5157,
      "step": 105
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 1.2137578254278512,
      "learning_rate": 1.2160178219764838e-05,
      "loss": 1.4907,
      "step": 110
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 1.2333755755507012,
      "learning_rate": 1.1395153389439232e-05,
      "loss": 1.4864,
      "step": 115
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.239317098102939,
      "learning_rate": 1.0621696374314807e-05,
      "loss": 1.4872,
      "step": 120
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.1935616120101977,
      "learning_rate": 9.844481880796492e-06,
      "loss": 1.5288,
      "step": 125
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 1.167038478793757,
      "learning_rate": 9.068207325159285e-06,
      "loss": 1.4918,
      "step": 130
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.2606116528575086,
      "learning_rate": 8.297564442776014e-06,
      "loss": 1.4989,
      "step": 135
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 1.2053439169353648,
      "learning_rate": 7.537210931679988e-06,
      "loss": 1.499,
      "step": 140
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 1.2078865568862998,
      "learning_rate": 6.791742301846325e-06,
      "loss": 1.5059,
      "step": 145
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.181773149819734,
      "learning_rate": 6.065664100332478e-06,
      "loss": 1.482,
      "step": 150
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 1.1586295971120542,
      "learning_rate": 5.3633646801467255e-06,
      "loss": 1.4776,
      "step": 155
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.1426794972054166,
      "learning_rate": 4.6890886774272485e-06,
      "loss": 1.4794,
      "step": 160
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 1.2053169655060443,
      "learning_rate": 4.046911357233343e-06,
      "loss": 1.4616,
      "step": 165
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 1.1647726703293662,
      "learning_rate": 3.440713983000601e-06,
      "loss": 1.4921,
      "step": 170
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.1515379297439883,
      "learning_rate": 2.8741603585249312e-06,
      "loss": 1.4614,
      "step": 175
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1677038359307508,
      "learning_rate": 2.3506746842535244e-06,
      "loss": 1.4821,
      "step": 180
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 1.157505348471252,
      "learning_rate": 1.8734208617174986e-06,
      "loss": 1.4643,
      "step": 185
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 1.1694689724300111,
      "learning_rate": 1.4452833711883629e-06,
      "loss": 1.4734,
      "step": 190
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 1.1512148511863012,
      "learning_rate": 1.0688498381320855e-06,
      "loss": 1.4435,
      "step": 195
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.1323651049667787,
      "learning_rate": 7.463953938275859e-07,
      "loss": 1.447,
      "step": 200
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 1.1423892630102332,
      "learning_rate": 4.798689246727006e-07,
      "loss": 1.4368,
      "step": 205
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 1.1409480033032104,
      "learning_rate": 2.708812932856253e-07,
      "loss": 1.4754,
      "step": 210
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 1.1449815403515953,
      "learning_rate": 1.206956025924333e-07,
      "loss": 1.473,
      "step": 215
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.1871235983216775,
      "learning_rate": 3.0219561743707326e-08,
      "loss": 1.4529,
      "step": 220
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1249933194182675,
      "learning_rate": 0.0,
      "loss": 1.4638,
      "step": 225
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4236433506011963,
      "eval_runtime": 54.2532,
      "eval_samples_per_second": 22.063,
      "eval_steps_per_second": 0.7,
      "step": 225
    },
    {
      "epoch": 1.0,
      "step": 225,
      "total_flos": 11777605632000.0,
      "train_loss": 1.5383918571472168,
      "train_runtime": 1636.4794,
      "train_samples_per_second": 4.388,
      "train_steps_per_second": 0.137
    }
  ],
  "logging_steps": 5,
  "max_steps": 225,
  "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": 11777605632000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}