{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23391812865497075,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 7.826007843017578,
      "learning_rate": 2e-05,
      "loss": 9.0283,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 2.5153708457946777,
      "eval_runtime": 12.1733,
      "eval_samples_per_second": 7.393,
      "eval_steps_per_second": 3.697,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 5.209957122802734,
      "learning_rate": 4e-05,
      "loss": 10.2824,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 6.798622131347656,
      "learning_rate": 6e-05,
      "loss": 9.3776,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 9.03697681427002,
      "learning_rate": 8e-05,
      "loss": 9.7456,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 8.008644104003906,
      "learning_rate": 0.0001,
      "loss": 7.9851,
      "step": 5
    },
    {
      "epoch": 0.023391812865497075,
      "eval_loss": 2.4577860832214355,
      "eval_runtime": 12.2165,
      "eval_samples_per_second": 7.367,
      "eval_steps_per_second": 3.684,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 5.449644565582275,
      "learning_rate": 0.00012,
      "loss": 8.7185,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 8.997721672058105,
      "learning_rate": 0.00014,
      "loss": 7.7083,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 11.64513111114502,
      "learning_rate": 0.00016,
      "loss": 7.014,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 13.062312126159668,
      "learning_rate": 0.00018,
      "loss": 7.7493,
      "step": 9
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 8.601241111755371,
      "learning_rate": 0.0002,
      "loss": 7.3621,
      "step": 10
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 1.8369699716567993,
      "eval_runtime": 12.2837,
      "eval_samples_per_second": 7.327,
      "eval_steps_per_second": 3.663,
      "step": 10
    },
    {
      "epoch": 0.05146198830409357,
      "grad_norm": 8.863720893859863,
      "learning_rate": 0.0001996917333733128,
      "loss": 5.9981,
      "step": 11
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 9.383522987365723,
      "learning_rate": 0.00019876883405951377,
      "loss": 6.74,
      "step": 12
    },
    {
      "epoch": 0.0608187134502924,
      "grad_norm": 6.839603424072266,
      "learning_rate": 0.00019723699203976766,
      "loss": 5.1847,
      "step": 13
    },
    {
      "epoch": 0.06549707602339182,
      "grad_norm": 8.921788215637207,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.3841,
      "step": 14
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 10.35289478302002,
      "learning_rate": 0.0001923879532511287,
      "loss": 4.4214,
      "step": 15
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 0.8018842339515686,
      "eval_runtime": 12.2435,
      "eval_samples_per_second": 7.351,
      "eval_steps_per_second": 3.675,
      "step": 15
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": 13.363290786743164,
      "learning_rate": 0.0001891006524188368,
      "loss": 3.2433,
      "step": 16
    },
    {
      "epoch": 0.07953216374269007,
      "grad_norm": 13.53653335571289,
      "learning_rate": 0.00018526401643540922,
      "loss": 2.4176,
      "step": 17
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 15.641883850097656,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.3459,
      "step": 18
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 9.132326126098633,
      "learning_rate": 0.0001760405965600031,
      "loss": 2.0361,
      "step": 19
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 8.304856300354004,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.7234,
      "step": 20
    },
    {
      "epoch": 0.0935672514619883,
      "eval_loss": 0.29656243324279785,
      "eval_runtime": 12.3271,
      "eval_samples_per_second": 7.301,
      "eval_steps_per_second": 3.651,
      "step": 20
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 8.58641529083252,
      "learning_rate": 0.00016494480483301836,
      "loss": 1.3902,
      "step": 21
    },
    {
      "epoch": 0.10292397660818714,
      "grad_norm": 5.155141830444336,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.077,
      "step": 22
    },
    {
      "epoch": 0.10760233918128655,
      "grad_norm": 11.07797622680664,
      "learning_rate": 0.0001522498564715949,
      "loss": 1.3385,
      "step": 23
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 6.937018394470215,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.8362,
      "step": 24
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 10.078267097473145,
      "learning_rate": 0.000138268343236509,
      "loss": 1.0317,
      "step": 25
    },
    {
      "epoch": 0.11695906432748537,
      "eval_loss": 0.20304298400878906,
      "eval_runtime": 12.2937,
      "eval_samples_per_second": 7.321,
      "eval_steps_per_second": 3.66,
      "step": 25
    },
    {
      "epoch": 0.1216374269005848,
      "grad_norm": 4.136928081512451,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5897,
      "step": 26
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 6.798682689666748,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.9892,
      "step": 27
    },
    {
      "epoch": 0.13099415204678364,
      "grad_norm": 4.000155925750732,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.6525,
      "step": 28
    },
    {
      "epoch": 0.13567251461988303,
      "grad_norm": 11.599156379699707,
      "learning_rate": 0.0001078459095727845,
      "loss": 1.2017,
      "step": 29
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 4.855947494506836,
      "learning_rate": 0.0001,
      "loss": 0.6204,
      "step": 30
    },
    {
      "epoch": 0.14035087719298245,
      "eval_loss": 0.15547069907188416,
      "eval_runtime": 12.3014,
      "eval_samples_per_second": 7.316,
      "eval_steps_per_second": 3.658,
      "step": 30
    },
    {
      "epoch": 0.14502923976608187,
      "grad_norm": 4.86682653427124,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.6178,
      "step": 31
    },
    {
      "epoch": 0.1497076023391813,
      "grad_norm": 5.159714698791504,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.6018,
      "step": 32
    },
    {
      "epoch": 0.1543859649122807,
      "grad_norm": 5.153872966766357,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.6714,
      "step": 33
    },
    {
      "epoch": 0.15906432748538013,
      "grad_norm": 4.7861175537109375,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6572,
      "step": 34
    },
    {
      "epoch": 0.16374269005847952,
      "grad_norm": 3.1466145515441895,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.5877,
      "step": 35
    },
    {
      "epoch": 0.16374269005847952,
      "eval_loss": 0.15545833110809326,
      "eval_runtime": 12.3106,
      "eval_samples_per_second": 7.311,
      "eval_steps_per_second": 3.655,
      "step": 35
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 4.603034973144531,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.6704,
      "step": 36
    },
    {
      "epoch": 0.17309941520467836,
      "grad_norm": 5.196393966674805,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.6149,
      "step": 37
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 3.324974536895752,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.4832,
      "step": 38
    },
    {
      "epoch": 0.1824561403508772,
      "grad_norm": 5.910963535308838,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.6351,
      "step": 39
    },
    {
      "epoch": 0.1871345029239766,
      "grad_norm": 3.9247097969055176,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.5944,
      "step": 40
    },
    {
      "epoch": 0.1871345029239766,
      "eval_loss": 0.14090923964977264,
      "eval_runtime": 12.2981,
      "eval_samples_per_second": 7.318,
      "eval_steps_per_second": 3.659,
      "step": 40
    },
    {
      "epoch": 0.19181286549707602,
      "grad_norm": 4.103235721588135,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.6428,
      "step": 41
    },
    {
      "epoch": 0.19649122807017544,
      "grad_norm": 3.029714822769165,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.5269,
      "step": 42
    },
    {
      "epoch": 0.20116959064327486,
      "grad_norm": 3.4757909774780273,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.6129,
      "step": 43
    },
    {
      "epoch": 0.20584795321637428,
      "grad_norm": 3.6499361991882324,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.4946,
      "step": 44
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.979522705078125,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.494,
      "step": 45
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 0.13597309589385986,
      "eval_runtime": 12.3086,
      "eval_samples_per_second": 7.312,
      "eval_steps_per_second": 3.656,
      "step": 45
    },
    {
      "epoch": 0.2152046783625731,
      "grad_norm": 4.307312488555908,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.548,
      "step": 46
    },
    {
      "epoch": 0.2198830409356725,
      "grad_norm": 3.6571176052093506,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.5205,
      "step": 47
    },
    {
      "epoch": 0.22456140350877193,
      "grad_norm": 4.104868412017822,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.5511,
      "step": 48
    },
    {
      "epoch": 0.22923976608187135,
      "grad_norm": 3.687596559524536,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.5262,
      "step": 49
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 3.051823377609253,
      "learning_rate": 0.0,
      "loss": 0.45,
      "step": 50
    },
    {
      "epoch": 0.23391812865497075,
      "eval_loss": 0.13652019202709198,
      "eval_runtime": 12.3063,
      "eval_samples_per_second": 7.313,
      "eval_steps_per_second": 3.657,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 80,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.25746627182592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}