{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04311273981461522,
  "eval_steps": 4,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008622547962923044,
      "grad_norm": 18.349796295166016,
      "learning_rate": 2e-05,
      "loss": 12.2382,
      "step": 1
    },
    {
      "epoch": 0.0008622547962923044,
      "eval_loss": 12.783363342285156,
      "eval_runtime": 42.0314,
      "eval_samples_per_second": 11.634,
      "eval_steps_per_second": 5.829,
      "step": 1
    },
    {
      "epoch": 0.0017245095925846087,
      "grad_norm": 18.404314041137695,
      "learning_rate": 4e-05,
      "loss": 12.818,
      "step": 2
    },
    {
      "epoch": 0.002586764388876913,
      "grad_norm": 18.81452178955078,
      "learning_rate": 6e-05,
      "loss": 12.2314,
      "step": 3
    },
    {
      "epoch": 0.0034490191851692174,
      "grad_norm": 18.826942443847656,
      "learning_rate": 8e-05,
      "loss": 12.0138,
      "step": 4
    },
    {
      "epoch": 0.0034490191851692174,
      "eval_loss": 10.487162590026855,
      "eval_runtime": 41.3199,
      "eval_samples_per_second": 11.834,
      "eval_steps_per_second": 5.929,
      "step": 4
    },
    {
      "epoch": 0.004311273981461522,
      "grad_norm": 23.916542053222656,
      "learning_rate": 0.0001,
      "loss": 10.8756,
      "step": 5
    },
    {
      "epoch": 0.005173528777753826,
      "grad_norm": 25.37953758239746,
      "learning_rate": 0.00012,
      "loss": 7.9933,
      "step": 6
    },
    {
      "epoch": 0.00603578357404613,
      "grad_norm": 36.603450775146484,
      "learning_rate": 0.00014,
      "loss": 6.8124,
      "step": 7
    },
    {
      "epoch": 0.006898038370338435,
      "grad_norm": 39.93467712402344,
      "learning_rate": 0.00016,
      "loss": 4.8259,
      "step": 8
    },
    {
      "epoch": 0.006898038370338435,
      "eval_loss": 1.5156302452087402,
      "eval_runtime": 41.4263,
      "eval_samples_per_second": 11.804,
      "eval_steps_per_second": 5.914,
      "step": 8
    },
    {
      "epoch": 0.007760293166630739,
      "grad_norm": 24.483657836914062,
      "learning_rate": 0.00018,
      "loss": 1.6681,
      "step": 9
    },
    {
      "epoch": 0.008622547962923045,
      "grad_norm": 20.87933921813965,
      "learning_rate": 0.0002,
      "loss": 1.6076,
      "step": 10
    },
    {
      "epoch": 0.009484802759215347,
      "grad_norm": 28.462326049804688,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.9284,
      "step": 11
    },
    {
      "epoch": 0.010347057555507652,
      "grad_norm": 7.382307529449463,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.5719,
      "step": 12
    },
    {
      "epoch": 0.010347057555507652,
      "eval_loss": 0.8780114650726318,
      "eval_runtime": 41.4971,
      "eval_samples_per_second": 11.784,
      "eval_steps_per_second": 5.904,
      "step": 12
    },
    {
      "epoch": 0.011209312351799956,
      "grad_norm": 23.78351402282715,
      "learning_rate": 0.00019723699203976766,
      "loss": 1.0036,
      "step": 13
    },
    {
      "epoch": 0.01207156714809226,
      "grad_norm": 6.90433406829834,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.6748,
      "step": 14
    },
    {
      "epoch": 0.012933821944384565,
      "grad_norm": 12.185566902160645,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.6046,
      "step": 15
    },
    {
      "epoch": 0.01379607674067687,
      "grad_norm": 19.96064567565918,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.9423,
      "step": 16
    },
    {
      "epoch": 0.01379607674067687,
      "eval_loss": 0.5733368992805481,
      "eval_runtime": 41.5222,
      "eval_samples_per_second": 11.777,
      "eval_steps_per_second": 5.9,
      "step": 16
    },
    {
      "epoch": 0.014658331536969174,
      "grad_norm": 13.482269287109375,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.4834,
      "step": 17
    },
    {
      "epoch": 0.015520586333261479,
      "grad_norm": 22.92808723449707,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.9821,
      "step": 18
    },
    {
      "epoch": 0.016382841129553783,
      "grad_norm": 19.03671646118164,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.8987,
      "step": 19
    },
    {
      "epoch": 0.01724509592584609,
      "grad_norm": 7.670022487640381,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.4543,
      "step": 20
    },
    {
      "epoch": 0.01724509592584609,
      "eval_loss": 0.8335480093955994,
      "eval_runtime": 41.5035,
      "eval_samples_per_second": 11.782,
      "eval_steps_per_second": 5.903,
      "step": 20
    },
    {
      "epoch": 0.018107350722138392,
      "grad_norm": 16.6032657623291,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.8973,
      "step": 21
    },
    {
      "epoch": 0.018969605518430695,
      "grad_norm": 7.4585185050964355,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.4621,
      "step": 22
    },
    {
      "epoch": 0.019831860314723,
      "grad_norm": 6.364231586456299,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.6574,
      "step": 23
    },
    {
      "epoch": 0.020694115111015304,
      "grad_norm": 20.26422882080078,
      "learning_rate": 0.00014539904997395468,
      "loss": 1.3692,
      "step": 24
    },
    {
      "epoch": 0.020694115111015304,
      "eval_loss": 1.0001345872879028,
      "eval_runtime": 41.524,
      "eval_samples_per_second": 11.776,
      "eval_steps_per_second": 5.9,
      "step": 24
    },
    {
      "epoch": 0.02155636990730761,
      "grad_norm": 7.076972961425781,
      "learning_rate": 0.000138268343236509,
      "loss": 0.3212,
      "step": 25
    },
    {
      "epoch": 0.022418624703599913,
      "grad_norm": 6.530824661254883,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6942,
      "step": 26
    },
    {
      "epoch": 0.02328087949989222,
      "grad_norm": 7.959903717041016,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.4833,
      "step": 27
    },
    {
      "epoch": 0.02414313429618452,
      "grad_norm": 10.797367095947266,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.9116,
      "step": 28
    },
    {
      "epoch": 0.02414313429618452,
      "eval_loss": 0.6466512680053711,
      "eval_runtime": 41.5138,
      "eval_samples_per_second": 11.779,
      "eval_steps_per_second": 5.902,
      "step": 28
    },
    {
      "epoch": 0.025005389092476828,
      "grad_norm": 7.114670276641846,
      "learning_rate": 0.0001078459095727845,
      "loss": 0.5407,
      "step": 29
    },
    {
      "epoch": 0.02586764388876913,
      "grad_norm": 3.2049789428710938,
      "learning_rate": 0.0001,
      "loss": 0.4781,
      "step": 30
    },
    {
      "epoch": 0.026729898685061437,
      "grad_norm": 9.187115669250488,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.591,
      "step": 31
    },
    {
      "epoch": 0.02759215348135374,
      "grad_norm": 5.867708206176758,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.7579,
      "step": 32
    },
    {
      "epoch": 0.02759215348135374,
      "eval_loss": 0.8243234753608704,
      "eval_runtime": 41.5067,
      "eval_samples_per_second": 11.781,
      "eval_steps_per_second": 5.903,
      "step": 32
    },
    {
      "epoch": 0.028454408277646046,
      "grad_norm": 10.666952133178711,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.9866,
      "step": 33
    },
    {
      "epoch": 0.029316663073938348,
      "grad_norm": 4.174076080322266,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6182,
      "step": 34
    },
    {
      "epoch": 0.030178917870230654,
      "grad_norm": 3.677931070327759,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.5182,
      "step": 35
    },
    {
      "epoch": 0.031041172666522957,
      "grad_norm": 3.110746145248413,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.4857,
      "step": 36
    },
    {
      "epoch": 0.031041172666522957,
      "eval_loss": 0.6007174849510193,
      "eval_runtime": 41.5227,
      "eval_samples_per_second": 11.777,
      "eval_steps_per_second": 5.9,
      "step": 36
    },
    {
      "epoch": 0.03190342746281526,
      "grad_norm": 7.616958141326904,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.5722,
      "step": 37
    },
    {
      "epoch": 0.032765682259107566,
      "grad_norm": 2.529907703399658,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.6252,
      "step": 38
    },
    {
      "epoch": 0.03362793705539987,
      "grad_norm": 2.642162322998047,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.4966,
      "step": 39
    },
    {
      "epoch": 0.03449019185169218,
      "grad_norm": 4.3184943199157715,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.723,
      "step": 40
    },
    {
      "epoch": 0.03449019185169218,
      "eval_loss": 0.6944137215614319,
      "eval_runtime": 41.5298,
      "eval_samples_per_second": 11.775,
      "eval_steps_per_second": 5.899,
      "step": 40
    },
    {
      "epoch": 0.03535244664798448,
      "grad_norm": 8.983128547668457,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.9108,
      "step": 41
    },
    {
      "epoch": 0.036214701444276784,
      "grad_norm": 7.468381881713867,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.7251,
      "step": 42
    },
    {
      "epoch": 0.03707695624056909,
      "grad_norm": 5.072237014770508,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.6101,
      "step": 43
    },
    {
      "epoch": 0.03793921103686139,
      "grad_norm": 1.7604542970657349,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.3938,
      "step": 44
    },
    {
      "epoch": 0.03793921103686139,
      "eval_loss": 0.6142096519470215,
      "eval_runtime": 41.5514,
      "eval_samples_per_second": 11.769,
      "eval_steps_per_second": 5.896,
      "step": 44
    },
    {
      "epoch": 0.0388014658331537,
      "grad_norm": 3.0202577114105225,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.4996,
      "step": 45
    },
    {
      "epoch": 0.039663720629446,
      "grad_norm": 2.956026077270508,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.4319,
      "step": 46
    },
    {
      "epoch": 0.040525975425738305,
      "grad_norm": 7.0847649574279785,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.7578,
      "step": 47
    },
    {
      "epoch": 0.04138823022203061,
      "grad_norm": 3.5891644954681396,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.4404,
      "step": 48
    },
    {
      "epoch": 0.04138823022203061,
      "eval_loss": 0.5961737036705017,
      "eval_runtime": 41.5297,
      "eval_samples_per_second": 11.775,
      "eval_steps_per_second": 5.899,
      "step": 48
    },
    {
      "epoch": 0.04225048501832292,
      "grad_norm": 4.563670635223389,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.6466,
      "step": 49
    },
    {
      "epoch": 0.04311273981461522,
      "grad_norm": 3.3956706523895264,
      "learning_rate": 0.0,
      "loss": 0.4625,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.85471820890112e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}